there were a lot of events recorded by gharchive.org of which 1,881,601 were push events containing 2,784,193 commit messages that amount to 167,862,852 characters filtered with words.py@e23d022007... to these 61 messages:
Life is one big road with lots of signs. So when you riding through the ruts, don't complicate your mind. Flee from hate, mischief and jealousy. Don't bury your thoughts, put your vision to reality. Wake Up and Live!
Globber balance overhaul (#3039)
Globber came out overtuned as shit and actually replicated some of the issues that we didn't want like the dreaded ChokePoint Boiler Torture Rebalances some issues that weren't forseen during the development nor TM stage of globber. This should be TM'd
General changes:
- Globber C/D 25 seconds > 30 seconds ( the temp nerf PR didnt actually fix this correctly)
- Fire deals 2x damage instead of 1.5x damage ( this needs significant testing and will likely be toned down)
- Acid spray doesn't stun at full distances anymore
Depending on TM feedback, I might switch between these two variants of this overhaul:
Rework variance 1: Keep zoom and current design while maintaining a little toughness [currently on]
- Armor 25 > 20
- Zoom halved 4 > 2
- Dropped health a tier: 650 > 600
- Fire deals 2x damage instead of 1.25x damage
- Globber C/D
Rework variance 2: Embrace the zoom removal
- Directional armor 10 base armor + 20 at the front. Flank a globber to kill it!
- Slight windup increase 5s > 6s
- Fire damage 1.25x > 1.5x
Fixes:
Screenshots & Videos
Put screenshots and videos here with an empty line between the
screenshots and the <details> tags.
🆑 Totalepicness
balance: Rebalances globber, which has come out overtuned. Globber now has reduced health, armor and zoom along with higher fire damage multiplier. /:cl:
Co-authored-by: Epicness [email protected] Co-authored-by: morrowwolf [email protected]
[MIRROR] Mimes can no longer write without breaking their vow. [MDB IGNORE] (#20841)
- Mimes can no longer write without breaking their vow. (#74674)
I feel this is gonna be unpopular with the lazy mime players.
Also, this is an idea I had in my backlog for a while now
This removes the Mime's ability to write on paper while they're on their vow of silence. This can be compared to hand language, which doesn't let you speak despite not being considered "talking", and PDA messaging, which does the same.
Mimes can still write with their pen, which is a nice invisible white color. I thought I would keep it in as I find that interaction funny to have a Mime give someone just a blank paper, unknowing that there's text on it. Spraycans/Telekinesis/Circuits are also left unaffected because they require actual effort to obtain (doing genetics, doing circuits, or printing spraycans which take a lot of inventory space and is limited), compared to paper which you can carry hundreds of papers around and is bountiful across the station.
I thought this was attempted at least once, but I can't find any PR that mentions it, so I'm shooting my shot to see if this is something we'd want.
Mimes using paper is a lazy way to bypass their one job gimmick: Emoting over talking.
If they get a job change, they can simply break their vow to access paper writing abilities, so this doesn't affect that really. It more-so hits the Mimes who uses the job for the free spells/healing abilities/etc, and bypasses the downsides (im aware its harder to get people to read paper than it is to talk to them, but you can literally get the mute quirk and itll have the same effect without being the whole job).
The point is, you don't get invisible walls for free; it comes at a cost of not being able to talk to people. If you want to talk, then break your vow, lose access to your Mime abilities, and remake it later when the cooldown is over. You're not meant to do both.
🆑 balance: Mimes can no longer write on paper without breaking their vow. /🆑
- Mimes can no longer write without breaking their vow.
Co-authored-by: John Willard [email protected]
Setting Guide for G4 My Little Pony's Equestria
A full setting guide for the universe of My Little Pony Friendship is Magic. Trying to blend show accuracy and tone with 5e's general heroic fantasy vibes, I've been maintaining this guide since I created it in 2016. Contains Races, Feats, Subclasses, Spells, Items mundane and magical, Religions, and more.
Ports mothroaches + Moth emotes (#1843)
Can you guess what this PR does? If you answered that it ports this pull request, this pull request, and a partial part of this one too, then you're right!
You can also craft moth plushies now. You just need some cloth, mothroach hide, and a heart!
silly little moth roaches and emotes, who wouldn't want them in the game?
🆑 add: Mothroaches are now a thing add: Moth laughter, chittering and squeaking /🆑
New Medical job: The Coroner (#75065)
HackMD: https://hackmd.io/RE9uRwSYSjCch17-OQ4pjQ?view
Feedback link: https://tgstation13.org/phpBB/viewtopic.php?f=10&t=33972
Adds a Coroner job to the game, they work in the Medical department and have their office in the Morgue. I was inspired to make this after I had played my first round on Paradise and messed around in there. The analyzer is copied from there (ParadiseSS13/Paradise#20957), and their jumpsuit is also mostly stolen from it (i just copied the color scheme onto our own suits).
Coroners can perform autopsies on people to see their stats, like this
They have access to Medbay, and on lowpop will get Pharmacy (to make their own formaldehyde). They also have their own Secure Morgue access for their office (doubles as a surgery room because they are edgelords or whatever) and the secure morgue trays.
Secure Morgue trays spawn with their beepers off and is only accessible by them, the CMO, and HoS. It's used to morgue Antagonists. Security's own morgue trays have been removed.
The job in action
Autopsies are a Surgery, and I tried to intertwine this with the Dissection surgery. Dissections and Autopsies both require the Autopsy scanner to perform them, however you can only perform one on any given body. Dissections are for experiments, Autopsies is for the paper of information.
Dissected bodies now also give a ~20% surgery speed boost, this was added at the request of Fikou as a way to encourage Doctors to let the Coroner do their job before reviving a body. I also remember the Medical skill, which allowed Doctors to do surgery faster on people, and I hope that this can do something like that WITHOUT adding the potential for exploiting, which led to the skill's downfall.
Morgue trays are no longer named with pens, they instead will steal the name of the last bodybag to be put in them.
Morgue trays are also removed from Brig Medical areas and Robotics, now they have to bring their corpses to the Morgue where the Coroner can keep track and ensure records are properly updated.
I can't fit it all in the Changelog, so this is who made what
McRamon
- Autopsy scanner
Tattax
- Table clock sprites and in-hands
CoiledLamb
- Coroner jumpsuits & labcoats (inhand, on sprite, and their respective alternatives)
- Coroner gloves
- CoronerDrobe (the vending machine)
This is mostly explained in the hackmd, but the goal of this is:
- Increase the use of the Medical Records console.
- Add a new and interesting way for Detectives to uncover mysteries.
- Add a more RP-flavored role in Medical that still has mechanics tied behind it.
🆑 JohnFulpWillard, sprites by McRamon, tattax, and Lamb add: The Coroner, a new Medical role revolving around dead corpses and autopsies. add: The Coroner's Autopsy Scanner, used for discovering the cause for someone's death, listing their wounds, the causes of them, their reagents, and diseases (including stealth ones!) qol: Morgue Trays are now named after the bodybags inside of them. balance: The morgue now has 'Secure' morgue trays which by default don't beep. balance: Security Medical area and Robotics no longer have their own morgue trays. balance: Dissected bodies now have faster surgery speed. Autopsies also count as dissections, however they're mutually exclusive. /🆑
Co-authored-by: Fikou [email protected]
Deadchat Announcement Variety Pack 1 (#75140)
Adds announce_to_ghosts()/notify_ghosts() calls to a bunch of different things.
THIS INCLUDES:
- Powersink being activated/reaching critical (explosion) heat capacity.
- His Grace being awoken.
- Hot Potatoes being armed.
- Ascension Rituals being completed.
- Eyesnatcher victims.
- Ovens exploding as a result of the Aurora Caelus event.
- Wizard Imposter spawns.
- Rock-Paper-Scissors with death as the result of Helbital consumption.
- BSA impact sites.
- Spontaneous Appendicitis.
- The purchasing of a badass syndie balloon.
- The Supermatter beginning to delaminate.
This was everything that I could think of that would be worth announcing to deadchat. These were all chosen with consideration to questions like "how easy would it be to spam deadchat with this?" and "will observers actually see the interesting thing happen, or just the aftermath?".
Not gonna lie, I've really become an observer main as of recently. Maybe that's being reflected in my recent PRs. Who's to say? Deadchat Announcement Variety Pack 2 will probably never come out. Sorry.
Gives deadchat a better indiciation of when/where something REALLY FUNNY is about to happen. Draws attention to certain things that are likely to gather an audience anyways, but sooner (for your viewing pleasure). In simple terms, it helps the observers observe things better.
Some cases, such as the aurora caelus or helbitaljanken, are occurrences so rare that they deserve the audience.
🆑 Rhials qol: Observers now recieve an alert when a powersink is activated/about to explode. qol: His Grace being awoken now alerts observers, to give you a headstart on your murderbone ghost ring. qol: Ascension Rituals being completed will also alert observers, for basically the same reason. qol: Arming a hot potato will now alert observers. Catch! qol: Eyesnatcher victims will now notify observers, and invite them to laugh at their state of misery and impotence. qol: Observers will be notified of any acute references to The Simpsons or other 20th Television America copyright properties. qol: Wizard Imposter spawns alert observers, much like any other ghost role event should. qol: Playing Rock-Paper-Scissors with death will now alert the observers and invite them to watch. Better not choke! qol: Observers now get an orbit link for BSA impact sites. Why does it keep teleporting me to the AI upload?? qol: Spontaneous Appendicitis now alerts deadchat. qol: The purchasing of a badass syndie balloon now alerts deadchat. You might not be any more powerful, but at least you have an audience. qol: When beginning to delaminate, the Supermatter will alert observers and invite them to watch the fireworks. /🆑
Demotes Psyker Pirates to Bounty Hunter Duty (#75031)
This PR demotes the Psyker-gang from a pirate team to a fugitive hunting team. For more information on Psyker pirates, please refer to #71650.
Stuff this also does in the process:
- Gives fugitive hunters their own subfolder in the fugitives antagonist folder, moves some of their stuff into hunter-specific files rather than interlacing it with the rest of the fugitive code.
- Moves the hunter backstories to defines, to make reading things easier while I made this change.
- Exhaustively moves everything related to psykers from being pirate-oriented to hunter-oriented (typepaths, locations where stuff is defined, etc. There should be nothing left behind related to psykers in anything pirate related). (Tell me if I missed anything somehow).
They still get their ship (they even get their own custom psyker-friendly prisoner capsule). They still have a bunch of lethally chambered firearms. They're the same gunrunning nutcases they were before, just as bounty hunters.
To assist with basic tasks such as "getting to the station" or "figuring out who the fuck we're supposed to be kidnapping", the psykers have "acquired" a Seer to assist them. They can try to coordinate the psykers and lead them through situations where their impairments put them at too great a disadvantage. If you're one of the psykers, make sure to keep this guy alive at all costs!
Why are they called Shikaris instead of hunters? Mariam-Webster says it's a Hindi word for some kind of hunter/tracker, and it sounded like something a bunch of space-junkies would call themselves because they think it sounds cool.
They now also come with a slightly different motivation, now that they can't directly threaten the crew for money. Psyker hunters now arrive tasked with a dirty kidnapping job, payment rendered in GORE.
Psykers aren't up to the challenge of being pirates. They're bogged down by a number of fundamental issues that render them unable to do anything expected of pirates. As it currently stands, they present about as much threat as you would expect from three blind junkies with guns.
Removing them wholesale would be kind of lame. They can function as a bunch of chaotic-neutral gun-toting space-maniacs, but for the purposes of gameplay, keeping them as pirates would be a waste of their talents.
Moving them to a lower-stakes role not only moves them to a niche they are more capable of filling, but gives players a more lax environment to get a grip on playing psyker without being overwhelmed.
Giving them a seeing-eye role should bring a more unique dynamic to how psykers are played (that is, some semblance of organization rather than blind flailing), and should help get over the mechanical hurdles of being a psyker until better solutions can be made. It shouldn't be too big of an impact on balance considering the psyker gang only has three spawns, while most hunter packs have 4+.
Allows Export of your Preferences JSON File (#75014)
Hey there,
This was spoken about in #70492 (specifically tgstation/tgstation#70492 (comment)), and I have been waiting for this to be implemented for some time. It never got implemented, so I decided to code it myself.
Basically, if the server host doesn't disable it, you are free to export your JSONs as a player, right from the stat-panel. It's a pretty JSON on 515 versions, too!
It's right here:
Here's what the prettified JSON looks like on 515.
There's a cooldown (default to 10 seconds) between exporting your preferences.
It's because in the past, a server host could always just file-share the
.sav or .json or whatever to the player, but they would have to do the
explicit option of actually bothering to make the files accessible to
the player. In that same line of logic, the server operator will have to
explicitly make the files accessible. This is mostly because I'm not
sure how good ftp() is at being a player function and wanted to have
some sort of cap/control somehow in case an exploit vector is detected
or it's just plain spammed by bots, so we'll just leave it up to the
direct providers of this data to elect if they wish to provide the data
or not.
Players don't have to log into Server A to remember what hairstyle they loved using when they want to swap to Server B! That's amazing actually. I always forget what ponytail my character has, and it'll be nice to have the hairstyle in a readily accessible place (after I prettify the JSON for myself).
It's also more convenient for server hosts to make player data like this accessible if they really want to, too.
If we ever add an import feature in the future (which would have to be done with a LOT of care), this will also be useful. I wouldn't advise it though having taken a precursory look at how much goes into it while trying to ascertain the scope of this PR.
🆑 qol: The game now supports export of your preferences into a JSON file! The verb (export-preferences) should now be available in the OOC tab of your stat-panel if enabled by server operators. server: Exporting player preferences is controlled by a configuration option, 'FORBID_PREFERENCES_EXPORT'. If you do not wish to let clients access the ftp() function to their own preferences file (probably for bandwidth reasons?) you should uncomment this or add it to your config somehow. config: Server operators are also able to set the cooldown between requests to download the JSON Preferences file via the 'SECONDS_COOLDOWN_FOR_PREFERENCES_EXPORT' config option. /🆑
Seriously this SHIT is starting to get on my fucking nerves... I want to go to bed.
New cards from MOC, MOM
March of the Machine Commander (MOC) March of the Machine (MOM) A few others from BRO and ONE Some old auras that get sacrificed at end of turn if you cast them as if they had flash fixed Fire Prophecy NEW: Umori, the Collector Rootwire Amalgam Steel Seraph Tyrranax Rex Paladin of Predation Axgard Artisan Zephyr Winder Phyrexian Pegasus Orthion, Hero of Lavabrink Surrak and Goreclaw Angelic Intervention Pile On Terror of Towashi Interdisciplinary Mascot Fertilid's Favor Vengeant Earth Sidar Jabari of Zhalfir Moira and Teshar Shalai and Hallar Vodalian Wave-Knight Bitterthorn, Nissa's Animus Herald of Hoofbeats Chivalric Alliance Darksteel Splicer Mistmeadow Vanisher Death-Greeter's Champion Hedron Detonator Pain Distributor Locthwain Lancer Schema Thief Exsanguinator Cavalry Nesting Dovehawk Filigree Vector Conjurer's Mantle Infernal Sovereign Firemane Commando Goro-Goro and Satoru Katilda and Lier Slimefoot and Squee Soar Armor of Thorns Grave Servitude Lightning Reflexes Spider Climb Parapet Mystic Veil Relic Ward Titania, Voice of Gaea Titania, Gaea Incarnate Professional Face-Breaker Oracle's Vault Volcanic Spite
Gunpoints now take half a second to activate, make gasp sounds, and briefly immobilize the shooter and target, other small balance changes (#74036)
This PR messes around with gunpoints a bit, with the purpose of making them more viable in certain scenarios without making them obnoxious. The biggest change is that gunpoints now require a 0.5 second do_after() where neither the shooter nor the target moves, and immobilizes both of them for 0.75 seconds if point blank, or half that if you're 2 tiles away. Originally you were supposed to only be able to initiate a gunpoint from point-blank, but #56601 seems to have removed that requirement, so we'll run with it and just leave it as advantageous to gunpoint closer up. The do_after() reinforces that it should be used as an ambush tactic, and so you can't use it on someone who's actively fleeing or fighting you.
Getting held up will now make you emit a shocked gasp sound, a la Metal Gear Solid, which combined with the short immobilize will hopefully make it more noticeable that someone's pointing a gun at you.
Holdups will now immediately give a 25% bonus to damage and wounds, instead of having to wait 2.5 seconds to hit the double damage stage.
Finally, right clicking someone that you're holding up will no longer shoot them. That just feels like good consistency.
Hopefully makes gunpoints a little more viable for when you want to stick someone who's not expecting it up without them immediately jetting off. In the future I'd like to ape Baycode and let the gunman have an action that toggles whether the victim is allowed to move, so you can order them to move to a second location without instantly shooting them, but that'll come later.
🆑 Ryll/Shaps balance: Holding someone at gunpoint now requires both the shooter and the victim to hold still for half a second before activating, so you can't hold-up people fleeing or fighting you. After that, it will briefly immobilize the both of you, 0.75 seconds if adjacent, or half that if you're two tiles away. Nuke ops are immune to the immobilization, since they're ready to die anyways. balance: Holding someone up will immediately apply a 1.25x damage and wound multiplier, rather than waiting 2.5 seconds to hit 2x. soundadd: Being held up will now make the victim play a sharp gasp sound, a la Metal Gear Solid. qol: Trying to hold someone up that you're already holding up will no longer shoot them. /🆑
Co-authored-by: san7890 [email protected]
fuck you i'll put an empty commit message if i want to
Fortnite battle pass. I just shit, out my ass. Bootin' up my PC, Because I need, need, To get that Fortnite battle pass. I like Fortnite, Did I mention Fortnite? I like Fortnite, It's night time, I mean it's five o'clock That's basically night time. Y'all remember cartoon network? Adventure time
Fortnite battle pass. I just shit, out my ass. Bootin' up my PC, Because I need, need, To get that Fortnite battle pass. I like Fortnite, Did I mention Fortnite? I like Fortnite, It's night time, I mean it's five o'clock That's basically night time. Y'all remember cartoon network? Adventure time
Metro: Refactor forceTapAnimation into TiltIndication
Fixes louis993546/Metro-Compose#192.
This was a real PITA to reverse engineer and figure out thanks to the
lackluster Indication and Interaction documentation.
The API is also missing some expected features like proper rotation
so instead we have to use android.graphics.Camera for the actual
tilting effect.
Hopefully my pain reverse engineering rememberRipple& co and then
subsequent sharing of a real-world reimplementation will prevent
future generations from having to suffer the same way I have.
Y'all have been forewarned, if you choose to tread where I've tread you'll only experience madness.
gpg-interface: set trust level of missing key to "undefined"
In check_signature(), we initialize the trust_level field to "-1", with the idea that if gpg does not return a trust level at all (if there is no signature, or if the signature is made by an unknown key), we'll use that value. But this has two problems:
-
Since the field is an enum, it's up to the compiler to decide what underlying storage to use, and it only has to fit the values we've declared. So we may not be able to store "-1" at all. And indeed, on my system (linux with gcc), the resulting enum is an unsigned 32-bit value, and -1 becomes 4294967295.
The difference may seem academic (and you even get "-1" if you pass it to printf("%d")), but it means that code like this:
status |= sigc->trust_level < configured_min_trust_level;
does not necessarily behave as expected. This turns out not to be a bug in practice, though, because we keep the "-1" only when gpg did not report a signature from a known key, in which case the line above:
status |= sigc->result != 'G';
would always set status to non-zero anyway. So only a 'G' signature with no parsed trust level would cause a problem, which doesn't seem likely to trigger (outside of unexpected gpg behavior).
-
When using the "%GT" format placeholder, we pass the value to gpg_trust_level_to_str(), which complains that the value is out of range with a BUG(). This behavior was introduced by 803978da49 (gpg-interface: add function for converting trust level to string, 2022-07-11). Before that, we just did a switch() on the enum, and anything that wasn't matched would end up as the empty string.
Curiously, solving this by naively doing:
if (level < 0) return "";
in that function isn't sufficient. Because of (1) above, the compiler can (and does in my case) actually remove that conditional as dead code!
We can solve both by representing this state as an enum value. We could do this by adding a new "unknown" value. But this really seems to match the existing "undefined" level well. GPG describes this as "Not enough information for calculation".
We have tests in t7510 that trigger this case (verifying a signature from a key that we don't have, and then checking various %G placeholders), but they didn't notice the BUG() because we didn't look at %GT for that case! Let's make sure we check all %G placeholders for each case in the formatting tests.
The interesting ones here are "show unknown signature with custom format" and "show lack of signature with custom format", both of which would BUG() before, and now turn %GT into "undefined". Prior to 803978da49 they would have turned it into the empty string, but I think saying "undefined" consistently is a reasonable outcome, and probably makes life easier for anyone parsing the output (and any such parser had to be ready to see "undefined" already).
The other modified tests produce the same output before and after this patch, but now we're consistently checking both %G? and %GT in all of them.
Signed-off-by: Jeff King [email protected] Reported-by: Rolf Eike Beer [email protected] Signed-off-by: Junio C Hamano [email protected]
http: support CURLOPT_PROTOCOLS_STR
The CURLOPT_PROTOCOLS (and matching CURLOPT_REDIR_PROTOCOLS) flag was deprecated in curl 7.85.0, and using it generate compiler warnings as of curl 7.87.0. The path forward is to use CURLOPT_PROTOCOLS_STR, but we can't just do so unilaterally, as it was only introduced less than a year ago in 7.85.0.
Until that version becomes ubiquitous, we have to either disable the deprecation warning or conditionally use the "STR" variant on newer versions of libcurl. This patch switches to the new variant, which is nice for two reasons:
-
we don't have to worry that silencing curl's deprecation warnings might cause us to miss other more useful ones
-
we'd eventually want to move to the new variant anyway, so this gets us set up (albeit with some extra ugly boilerplate for the conditional)
There are a lot of ways to split up the two cases. One way would be to abstract the storage type (strbuf versus a long), how to append (strbuf_addstr vs bitwise OR), how to initialize, which CURLOPT to use, and so on. But the resulting code looks pretty magical:
GIT_CURL_PROTOCOL_TYPE allowed = GIT_CURL_PROTOCOL_TYPE_INIT; if (...http is allowed...) GIT_CURL_PROTOCOL_APPEND(&allowed, "http", CURLOPT_HTTP);
and you end up with more "#define GIT_CURL_PROTOCOL_TYPE" macros than actual code.
On the other end of the spectrum, we could just implement two separate functions, one that handles a string list and one that handles bits. But then we end up repeating our list of protocols (http, https, ftp, ftp).
This patch takes the middle ground. The run-time code is always there to handle both types, and we just choose which one to feed to curl.
Signed-off-by: Jeff King [email protected] Signed-off-by: Junio C Hamano [email protected] Signed-off-by: Johannes Schindelin [email protected]
power: Introduce OnePlus 3 fingerprintd thaw hack
Taken from Oneplus 3, this hack will make fingerprintd recover from suspend quickly.
Small fixes for newer kernels since we're coming from 3.10.108..
Change-Id: I0166e82d51a07439d15b41dbc03d7e751bfa783b Co-authored-by: Cyber Knight [email protected] [cyberknight777: forwardport and adapt to 4.14] Signed-off-by: Shreyansh Lodha [email protected] Signed-off-by: Pierre2324 [email protected] Signed-off-by: PainKiller3 [email protected] Signed-off-by: Dhruv [email protected] Signed-off-by: Cyber Knight [email protected]
annoying gh 1
I hate these asshole roofers that my apartment brought out here they are making life miserable.
Created Text For URL [nypost.com/2023/05/05/tennessee-hotel-guest-wakes-up-to-night-manager-sucking-on-his-toes-police/]
[SQUASHED] core: Blacklist pixel system feature from Google Photos
We want to include the P21 experience flag to enable new features,
however it seems like Google Photos uses it to decide whether to use the
TPU tflite delegate. There doesn't seem to be any fallback so we need to
make sure the feature is not exposed to the app so that a normal
NNAPI/GPU delegate can be used instead.
Test: Google Photos editor with PIXEL_2021_EXPERIENCE feature in product
Signed-off-by: Kuba Wojciechowski <[email protected]>
Change-Id: I51a02f8347324c7a85f3136b802dce4cc4556ac5
commit 67eb31b3bb43d06fcc7f6fdb2f92eb486451cae6 Author: kondors1995 [email protected] Date: Thu Jun 9 17:39:25 2022 +0530
Core: Extend Pixel experience Blacklist For Google Photos
Turns out having these brakes Original quality backups.
Since these indicate that the device is pixel 4 with in the turn brakes device spoofing as OG pixel
Change-Id: I336facff7b55552f094997ade337656461a0ea1d
commit 508a99cde60b73dc3f1e843d569bca31def35988 Author: ReallySnow [email protected] Date: Fri Dec 31 16:40:23 2021 +0800
base: core: Blacklist Pixel 2017 and 2018 exclusive for Google Photos
* In this way can use PixelPropsUtils to simulate the Pixel XL prop
method to use the unlimited storage space of Google Photos
* Thanks nullbytepl for the idea
Change-Id: I92d472d319373d648365c8c63e301f1a915f8de9
commit aaf07f6ccc89c2747b97bc6dc2ee4cb7bd2c6727 Author: Akash Srivastava [email protected] Date: Sat Aug 20 19:04:32 2022 +0700
core: Pixel experience Blacklist For Google Photos for Android 13
* See, in Android 13 pixel_experience_2022_midyear was added, which needs to be blacklisted aswell
Change-Id: Id36d12afeda3cf6b39d01a0dbe7e3e9058659b8e
commit 9d6e5749a988c9051b1d47c11bb02daa7b1b36fd Author: spezi77 [email protected] Date: Mon Jan 31 19:17:34 2022 +0100
core: Rework the ph0t0s features blacklist
* Moving the flags to an array feels more like a blacklist :P
* Converted the flags into fully qualified package names, while at it
Signed-off-by: spezi77 <[email protected]>
Change-Id: I4b9e925fc0b8c01204564e18b9e9ee4c7d31c123
commit d7201c0cff326a6374e29aa79c6ce18828f96dc6 Author: Joey Huab [email protected] Date: Tue Feb 15 17:32:11 2022 +0900
core: Refactor Pixel features
* Magic Eraser is wonky and hard to
enable and all this mess isn't really worth
the trouble so just stick to the older setup.
* Default Pixel 5 spoof for Photos and only switch
to Pixel XL when spoof is toggled.
* We will try to bypass 2021 features and Raven
props for non-Pixel 2021 devices as apps usage
requires TPU.
* Remove P21 experience system feature check
Change-Id: Iffae2ac87ce5428daaf6711414b86212814db7f2
Adds the Dark Matt-eor when you emag a stupid amount of meteor shields + lots of meteor file sorting + qol + dark matter singularity + dark matt-eor summoning final traitor objective (#74330)
Dark Matt-eor Image
A barely visible blur in the cosmic darkness, like a ghostly shadow on a moonless night. A piercing howl in the vacuum of space, as if it were tearing the fabric of reality. A twisted halo of light around it, bending and breaking the rays of distant suns. A shower of quantum sparks, flickering and fading in its wake. A dark matter meteor (dark matt-eor) is a wonder to witness, and to dread.
A sudden impact, like a hammer blow to the heart of the station. A violent tremor, shaking and shattering the metal walls and windows. A deafening roar, as the air rushes out of the breached hull. A blinding flash, as the dark matter meteor unleashes its hidden energy. A tiny black hole, forming and growing in the center of the station. A relentless pull, dragging everything towards the abyss. A dark matter meteor is incredibly deadly.
Emagging too many meteor shields will summon a dark matt-eor. This comes with several warnings, and after awhile, warns the station that someone is trying to summon a dark matteor.
The dark matt-eor itself is not that damaging in its impact, but drops a singularity in its final resting place.
It's a new way to terrorize a round as an antagonist. Before, emagging a lot of meteor shields would basically make meteor showers the only event that can run, which is cool, but since constant meteor waves are going to destroy the station, let's also throw in the mother of all meteors!
This also adds warnings to spamming emagging meteor shields, which imo needs it. The round ends when someone spams emagged meteor shields, and since they're meteor shields nobody is going to reasonably check on them.
🆑 add: The dark matt-eor add: Summon a dark matt-eor final traitor objective add: Dark matter singularity variant, which can't grow as big as a regular singularity but hungers for blood code: cleaned up/sorted meteor shield code, satellite control, and more qol: added a lot of feedback to interacting with meteor shields balance: emagging a lot of meteor shields warns the station, but emagging enough of them summons a Dark Matt-eor. /🆑
Lints Against Unmanaged Local Defines (#74333)
TO AUTO-MERGE! IT'S MUCH EASIER FOR ME TO FIX THINGS BEFORE THEY SKEW RATHER THAN AFTER THE FACT.
Hey there,
This took a while to do, but here's the gist:
Python file now regexes every file in /code except for those that have
some valid reason to be tacking on more global defines. Some of those
reasons are simply just that I don't have the time right now (doing what
you see in this PR took a few hours) to refactor and parse what should
belong and what should be thrown out. For the time being though, this PR
will at least halt people making the mistake of not #undefing any
files they #define "locally", or within the scope of a file.
Most people forget to do this and this leads to a lot of mess later on due to how many variables can be unmanaged on the global level. I've made this mistake, you've made this mistake, it's a common thing. Let's automatically check for it so it can be fixed no-stress.
Scenarios this PR corrects:
- Forgetting to undef a define but undeffing others.
- Not undeffing any defines in your file.
- Earmarking a define as a "file local" define, but not defining it.
- Having a define be a "file local" define, but having it be used elsewhere.
- Having a "local" define not even be in the file that it only shows up in.
- Having a completely unused define*
(* I kept some of these because they seemed important... Others were junked.)
If you wanna use it across multiple files, no reason to not make it a global define (maybe there's a few reasons but let's assume that this is the 95% case).
Let me know if you don't like how I re-arranged some of the defines and how you'd rather see it be implemented, and I'd be happy to do that. This was mostly just "eh does it need it or not" sorta stuff.
I used a pretty cool way to detect if we should use the standardized GitHub "error" output, you can see the results of that here https://github.com/san7890/bruhstation/actions/runs/4549766579/jobs/8022186846#step:7:792
Nothing that really concerns players.
(I fixed up all this stuff using vscode, no regexes beyond what you see in the python script. sorry downstreams)
Assignment_4.1
You're going to write a movie storybook by acting in it with your teammates and friends. You're going to take pictures of key scenes in the movie, turn them into cartoons to make the pictures look like drawings, then stage and direct the pictures into the production of the storybook of a movie. You will pick one of the contenders for this year's American, Chinese, or Hindi Oscars (or the movie you like) as the base story and then modify it in a creative way.
You'll be in a team of 2, 3, or 4 students. There will be two submissions per team: i) The storybook as a PDF file, an English version, and a version in your language. The whole story book needs to have at least 5 pages (excluding the poster page), and each page needs to have around 20 pictures. ii) The software for the entire storybook. You are not allowed to stitch pictures together with paintbrush programs; it all needs to be in Python.
Manually hide our DesktopWindowXamlSource (#15165)
As discussed in #6507
Newer builds of Windows do this automatically. However, this was spotted in the wild on 1.18. It's possible the threading changes created a situation where the OS-side fix no longer applied to us. So let's just do it manually. It doesn't have any side effects.
I saw this once on Win11, but couldn't repro it this morning when I tried to add this fix. I'm just gonna assume this worked, despite the fact that I can't repro it on win11 anymore.
closes #6507
See also #14957
WindowsXamlManager::XamlCore::InitializecallsConfigureCoreWindow, which creates aCoreWindowon the thread
Problem is, we're calling that on the main thread (which doesn't have any windows), and then eventually creating a
DesktopWindowXamlSourceon a second thread for the actual window
It's not that it "manages a window", it's that it "manages xaml on Windows OS". just use ICoreWindowInterop -- QI for ICoreWindowInterop and call get_WindowHandle.
Also see: * ICoreWindowInterop * WindowsXamlManager.InitializeForCurrentThread
- The source code in
onecoreuap\windows\dxaml\xcp\dxaml\lib\WindowsXamlManager_Partial.* - os.2020!6102020 which fixed MSFT:33498969, MSFT:27807465, MSFT:21854264
BACKPORT: signal: add pidfd_send_signal() syscall
The kill() syscall operates on process identifiers (pid). After a process has exited its pid can be reused by another process. If a caller sends a signal to a reused pid it will end up signaling the wrong process. This issue has often surfaced and there has been a push to address this problem [1].
This patch uses file descriptors (fd) from proc/ as stable handles on struct pid. Even if a pid is recycled the handle will not change. The fd can be used to send signals to the process it refers to. Thus, the new syscall pidfd_send_signal() is introduced to solve this problem. Instead of pids it operates on process fds (pidfd).
/* prototype and argument /* long pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags);
/* syscall number 424 */ The syscall number was chosen to be 424 to align with Arnd's rework in his y2038 to minimize merge conflicts (cf. [25]).
In addition to the pidfd and signal argument it takes an additional siginfo_t and flags argument. If the siginfo_t argument is NULL then pidfd_send_signal() is equivalent to kill(, ). If it is not NULL pidfd_send_signal() is equivalent to rt_sigqueueinfo(). The flags argument is added to allow for future extensions of this syscall. It currently needs to be passed as 0. Failing to do so will cause EINVAL.
/* pidfd_send_signal() replaces multiple pid-based syscalls */ The pidfd_send_signal() syscall currently takes on the job of rt_sigqueueinfo(2) and parts of the functionality of kill(2), Namely, when a positive pid is passed to kill(2). It will however be possible to also replace tgkill(2) and rt_tgsigqueueinfo(2) if this syscall is extended.
/* sending signals to threads (tid) and process groups (pgid) */ Specifically, the pidfd_send_signal() syscall does currently not operate on process groups or threads. This is left for future extensions. In order to extend the syscall to allow sending signal to threads and process groups appropriately named flags (e.g. PIDFD_TYPE_PGID, and PIDFD_TYPE_TID) should be added. This implies that the flags argument will determine what is signaled and not the file descriptor itself. Put in other words, grouping in this api is a property of the flags argument not a property of the file descriptor (cf. [13]). Clarification for this has been requested by Eric (cf. [19]). When appropriate extensions through the flags argument are added then pidfd_send_signal() can additionally replace the part of kill(2) which operates on process groups as well as the tgkill(2) and rt_tgsigqueueinfo(2) syscalls. How such an extension could be implemented has been very roughly sketched in [14], [15], and [16]. However, this should not be taken as a commitment to a particular implementation. There might be better ways to do it. Right now this is intentionally left out to keep this patchset as simple as possible (cf. [4]).
/* naming */ The syscall had various names throughout iterations of this patchset:
- procfd_signal()
- procfd_send_signal()
- taskfd_send_signal() In the last round of reviews it was pointed out that given that if the flags argument decides the scope of the signal instead of different types of fds it might make sense to either settle for "procfd_" or "pidfd_" as prefix. The community was willing to accept either (cf. [17] and [18]). Given that one developer expressed strong preference for the "pidfd_" prefix (cf. [13]) and with other developers less opinionated about the name we should settle for "pidfd_" to avoid further bikeshedding.
The "_send_signal" suffix was chosen to reflect the fact that the syscall takes on the job of multiple syscalls. It is therefore intentional that the name is not reminiscent of neither kill(2) nor rt_sigqueueinfo(2). Not the fomer because it might imply that pidfd_send_signal() is a replacement for kill(2), and not the latter because it is a hassle to remember the correct spelling - especially for non-native speakers - and because it is not descriptive enough of what the syscall actually does. The name "pidfd_send_signal" makes it very clear that its job is to send signals.
/* zombies */ Zombies can be signaled just as any other process. No special error will be reported since a zombie state is an unreliable state (cf. [3]). However, this can be added as an extension through the @flags argument if the need ever arises.
/* cross-namespace signals */ The patch currently enforces that the signaler and signalee either are in the same pid namespace or that the signaler's pid namespace is an ancestor of the signalee's pid namespace. This is done for the sake of simplicity and because it is unclear to what values certain members of struct siginfo_t would need to be set to (cf. [5], [6]).
/* compat syscalls */ It became clear that we would like to avoid adding compat syscalls (cf. [7]). The compat syscall handling is now done in kernel/signal.c itself by adding __copy_siginfo_from_user_generic() which lets us avoid compat syscalls (cf. [8]). It should be noted that the addition of __copy_siginfo_from_user_any() is caused by a bug in the original implementation of rt_sigqueueinfo(2) (cf. 12). With upcoming rework for syscall handling things might improve significantly (cf. [11]) and __copy_siginfo_from_user_any() will not gain any additional callers.
/* testing */ This patch was tested on x64 and x86.
/* userspace usage */ An asciinema recording for the basic functionality can be found under [9]. With this patch a process can be killed via:
#define _GNU_SOURCE #include <errno.h> #include <fcntl.h> #include <signal.h> #include <stdio.h> #include <stdlib.h> #include <string.h> #include <sys/stat.h> #include <sys/syscall.h> #include <sys/types.h> #include <unistd.h>
static inline int do_pidfd_send_signal(int pidfd, int sig, siginfo_t *info, unsigned int flags) { #ifdef __NR_pidfd_send_signal return syscall(__NR_pidfd_send_signal, pidfd, sig, info, flags); #else return -ENOSYS; #endif }
int main(int argc, char *argv[]) { int fd, ret, saved_errno, sig;
if (argc < 3)
exit(EXIT_FAILURE);
fd = open(argv[1], O_DIRECTORY | O_CLOEXEC);
if (fd < 0) {
printf("%s - Failed to open \"%s\"\n", strerror(errno), argv[1]);
exit(EXIT_FAILURE);
}
sig = atoi(argv[2]);
printf("Sending signal %d to process %s\n", sig, argv[1]);
ret = do_pidfd_send_signal(fd, sig, NULL, 0);
saved_errno = errno;
close(fd);
errno = saved_errno;
if (ret < 0) {
printf("%s - Failed to send signal %d to process %s\n",
strerror(errno), sig, argv[1]);
exit(EXIT_FAILURE);
}
exit(EXIT_SUCCESS);
}
/* Q&A
- Given that it seems the same questions get asked again by people who are
- late to the party it makes sense to add a Q&A section to the commit
- message so it's hopefully easier to avoid duplicate threads.
- For the sake of progress please consider these arguments settled unless
- there is a new point that desperately needs to be addressed. Please make
- sure to check the links to the threads in this commit message whether
- this has not already been covered. */ Q-01: (Florian Weimer [20], Andrew Morton [21]) What happens when the target process has exited? A-01: Sending the signal will fail with ESRCH (cf. [22]).
Q-02: (Andrew Morton [21]) Is the task_struct pinned by the fd? A-02: No. A reference to struct pid is kept. struct pid - as far as I understand - was created exactly for the reason to not require to pin struct task_struct (cf. [22]).
Q-03: (Andrew Morton [21]) Does the entire procfs directory remain visible? Just one entry within it? A-03: The same thing that happens right now when you hold a file descriptor to /proc/ open (cf. [22]).
Q-04: (Andrew Morton [21]) Does the pid remain reserved? A-04: No. This patchset guarantees a stable handle not that pids are not recycled (cf. [22]).
Q-05: (Andrew Morton [21]) Do attempts to signal that fd return errors? A-05: See {Q,A}-01.
Q-06: (Andrew Morton [22]) Is there a cleaner way of obtaining the fd? Another syscall perhaps. A-06: Userspace can already trivially retrieve file descriptors from procfs so this is something that we will need to support anyway. Hence, there's no immediate need to add another syscalls just to make pidfd_send_signal() not dependent on the presence of procfs. However, adding a syscalls to get such file descriptors is planned for a future patchset (cf. [22]).
Q-07: (Andrew Morton [21] and others) This fd-for-a-process sounds like a handy thing and people may well think up other uses for it in the future, probably unrelated to signals. Are the code and the interface designed to permit such future applications? A-07: Yes (cf. [22]).
Q-08: (Andrew Morton [21] and others) Now I think about it, why a new syscall? This thing is looking rather like an ioctl? A-08: This has been extensively discussed. It was agreed that a syscall is preferred for a variety or reasons. Here are just a few taken from prior threads. Syscalls are safer than ioctl()s especially when signaling to fds. Processes are a core kernel concept so a syscall seems more appropriate. The layout of the syscall with its four arguments would require the addition of a custom struct for the ioctl() thereby causing at least the same amount or even more complexity for userspace than a simple syscall. The new syscall will replace multiple other pid-based syscalls (see description above). The file-descriptors-for-processes concept introduced with this syscall will be extended with other syscalls in the future. See also [22], [23] and various other threads already linked in here.
Q-09: (Florian Weimer [24]) What happens if you use the new interface with an O_PATH descriptor? A-09: pidfds opened as O_PATH fds cannot be used to send signals to a process (cf. [2]). Signaling processes through pidfds is the equivalent of writing to a file. Thus, this is not an operation that operates "purely at the file descriptor level" as required by the open(2) manpage. See also [4].
/* References */ [1]: https://lore.kernel.org/lkml/[email protected]/ [2]: https://lore.kernel.org/lkml/[email protected]/ [3]: https://lore.kernel.org/lkml/[email protected]/ [4]: https://lore.kernel.org/lkml/[email protected]/ [5]: https://lore.kernel.org/lkml/[email protected]/ [6]: https://lore.kernel.org/lkml/[email protected]/ [7]: https://lore.kernel.org/lkml/[email protected]/ [8]: https://lore.kernel.org/lkml/[email protected]/ [9]: https://asciinema.org/a/IQjuCHew6bnq1cr78yuMv16cy [11]: https://lore.kernel.org/lkml/[email protected]/ [12]: https://lore.kernel.org/lkml/[email protected]/ [13]: https://lore.kernel.org/lkml/[email protected]/ [14]: https://lore.kernel.org/lkml/[email protected]/ [15]: https://lore.kernel.org/lkml/[email protected]/ [16]: https://lore.kernel.org/lkml/[email protected]/ [17]: https://lore.kernel.org/lkml/CAGXu5jL8PciZAXvOvCeCU3wKUEB_dU-O3q0tDw4uB_ojMvDEew@mail.gmail.com/ [18]: https://lore.kernel.org/lkml/[email protected]/ [19]: https://lore.kernel.org/lkml/[email protected]/ [20]: https://lore.kernel.org/lkml/[email protected]/ [21]: https://lore.kernel.org/lkml/[email protected]/ [22]: https://lore.kernel.org/lkml/[email protected]/ [23]: https://lwn.net/Articles/773459/ [24]: https://lore.kernel.org/lkml/[email protected]/ [25]: https://lore.kernel.org/lkml/CAK8P3a0ej9NcJM8wXNPbcGUyOUZYX+VLoDFdbenW3s3114oQZw@mail.gmail.com/
Cc: "Eric W. Biederman" [email protected] Cc: Jann Horn [email protected] Cc: Andy Lutomirsky [email protected] Cc: Andrew Morton [email protected] Cc: Oleg Nesterov [email protected] Cc: Al Viro [email protected] Cc: Florian Weimer [email protected] Signed-off-by: Christian Brauner [email protected] Reviewed-by: Tycho Andersen [email protected] Reviewed-by: Kees Cook [email protected] Reviewed-by: David Howells [email protected] Acked-by: Arnd Bergmann [email protected] Acked-by: Thomas Gleixner [email protected] Acked-by: Serge Hallyn [email protected] Acked-by: Aleksa Sarai [email protected]
(cherry picked from commit 3eb39f47934f9d5a3027fe00d906a45fe3a15fad)
Conflicts: arch/x86/entry/syscalls/syscall_32.tbl - trivial manual merge arch/x86/entry/syscalls/syscall_64.tbl - trivial manual merge include/linux/proc_fs.h - trivial manual merge include/linux/syscalls.h - trivial manual merge include/uapi/asm-generic/unistd.h - trivial manual merge kernel/signal.c - struct kernel_siginfo does not exist in 4.14 kernel/sys_ni.c - cond_syscall is used instead of COND_SYSCALL arch/x86/entry/syscalls/syscall_32.tbl arch/x86/entry/syscalls/syscall_64.tbl
(1. manual merges because of 4.14 differences 2. change prepare_kill_siginfo() to use struct siginfo instead of kernel_siginfo 3. use copy_from_user() instead of copy_siginfo_from_user() in copy_siginfo_from_user_any() 4. replaced COND_SYSCALL with cond_syscall 5. Removed __ia32_sys_pidfd_send_signal in arch/x86/entry/syscalls/syscall_32.tbl. 6. Replaced __x64_sys_pidfd_send_signal with sys_pidfd_send_signal in arch/x86/entry/syscalls/syscall_64.tbl.)
Bug: 135608568 Test: test program using syscall(__NR_pidfd_send_signal,..) to send SIGKILL Change-Id: I34da11c63ac8cafb0353d9af24c820cef519ec27 Signed-off-by: Suren Baghdasaryan [email protected] Signed-off-by: electimon [email protected]
100th note to self about the same thing: Commit more often
STUFF THAT HAS CHANGED (HOLY FUCK ITS ALOT)
- Removed a bunch of unnecessary code
- Did so you can't break bombs after having placed them down.
- Added Token History and Token Check
- Changed the bomb explosion to look like an explosion
- Implemented NUKE
- Streamlined the nuke explosion to not have any switch cases or anything like that
- Added /purchases
- Fixed econcheck as it was semi broken
- Found out Ive been using the wrong hour measurement for moneyhistory, so all of those logs are in 12 hour time without the am / pm so you dont really know when on the day it took place, but Ive now fixed that.
- Added a /minereset command to better reset the mines
- Added /voucher so that I can add different vouchers like mine-reset and token-shop.
- Did so if the dailyMission is make money it'll add a $ infront
- Added libsDisguises dependency for a future project
- Moved Purpur dependency to the top of the dependencies list as I've come to realize that the dependencies works in a hierarchy.
- Added a /virtualfurnace to test out the possibility of a virtual furnace.
- Started work on custom coding the tokenshop as the current one thats made with the panels plugin is missing some stuff we'd like to add.
- Probably more
updates for landing zone sign sprites (#3180)
Cleans up the palettes on the landing zone sign sprites and gives them a fresh coat of paint (or blood). Not something most people will notice I think but it's something I've been wanting to do.
gradients ugly
Click to see sprites
🆑 imageadd: new sprites for landing zone signs imagedel: deleted old landing zone signs /🆑
[MIRROR] Completing experiments after their associated nodes have been researched gives back a partial refund of the discount lost [MDB IGNORE] (#19743)
- Completing experiments after their associated nodes have been researched gives back a partial refund of the discount lost (#73814)
So we're like simultaneously moving two vague directions with research. One being "experisci grants discounts for prohibitively expensive nodes so you want to do the experiments to discount them" and the other being "Let's give Heads of Staff a way to research anything they want without any communication to the research department, including the very expensive nodes that scientists may be working on"
You already see the issue, right? You can't have your cake and eat it too.
It sucks for scientists to be working on a complex experiment like weapons tech for that huge 90% discount only for the HoS to stumble onto the bridge and research it anyways. Your time is wasted and RND is slowed down massively.
We can do something to assuage that.
This PR makes it so completing an experiment which discounts already completed nodes will refund a partial amount of the discount that would've applied.
For example, researching industrial engineering without scanning the iron toilets will refund ~5000 points.
This can only apply once per experiment, so if an experiment discounts multiple technologies, they will only get a refund based on the first technology researched.
This accomplishes the following:
- Expensive research nodes with difficult experiments remain expensive without completing the experiments. If no one does the experiment, they act the same as before.
- Expensive research nodes with very easy experiments (but time consuming) no longer put RND on a time crunch to beat the itchy trigger finger of the Heads of Staff. Stuff like scanning lathes allow the scientists to work more at their own pace: they can talk to people or maybe stop at the bar or kitchen between departments without feeling pressure to get it done urgently.
- Scientists are able to complete experiments which previously were no longer deemed relevant if they need a point injection. Experiments left behind are no longer completely useless bricks. Maybe even gives latejoin scientists something to do.
- Scientists mid experiment can still complete it to not feel like their time is wasted.
Overall I think this has many benefits to the current science system where many have complaints.
🆑 Melbert qol: Completing an experiment which discounts a researched tech node will give a partial refund of the discount lost. For example, researching the industrial engineering research without scanning iron toilets will refund ~5000 points if you complete it afterwards. This only applies once per experiment, so experiments which discount multiple nodes only refund the first researched. /🆑
Co-authored-by: san7890 <the@ san7890.com>
- Completing experiments after their associated nodes have been researched gives back a partial refund of the discount lost
Co-authored-by: MrMelbert [email protected] Co-authored-by: san7890 <the@ san7890.com>
Add Kurtosis to list of testing tools (#1063)
- Add Kurtosis to list of testing tools
Hey team! We'd like to add Kurtosis to the list of testing tools.
What is Kurtosis? Kurtosis is a built system for multi-(docker)container test environments. What is Kurtosis for? Kurtosis is for engineers who dev against large distributed systems/applications and who experience pain when trying to configure multi (Docker) container environments for their testing workflows.
Kurtosis can be used locally without the need to sign up and is free-forever under a source-available license (BSL).
We have:
- Linked out to our Github: https://github.com/kurtosis-tech/kurtosis
- A README on our GIthub
- Content about how to setup/install the project (in our Github README and on our docs),
- Lots of great examples on: Github and in our docs.
I followed the Quality Standards you guys wrote, but please let me know if you've got any questions about Kurtosis or if we missed something!
Thanks
- add "composable" to description
changed this stupid fucking bitch aka printing of this stupid shit
[DNM][HACK] telephony: Force Class 0 SMS to Class 1
This kills Flash SMS messages. Fuck you airtel
Change-Id: Ifb0c9e8bae5c12868d178fbdaeceb2cc72a0ffb6
steam beta changed class to 'steam'
THIS IS SO FUCKING STUPID OH MY FUCKING GOD WHYYYYY
Healer Balance Changes (#2896)
This pull request addresses the boring and low-risk gameplay of the Healer drone, who spends half the round sitting next to recovery nodes and recovering her health so she may use it again, rinse and repeat until a rine notices said drone has purple on it and booms her.
First, by changing her health from 600 to 500, Healer can spend more time healing her sisters than sitting through another 100 health to heal herself. Though this makes her less tanky than before, healing classes are not known to be tanks. To ensure Healer can still heal five times without depleting too much of her health whilst still giving her sisters a decent amount of heals, I made her ability cost 75 health instead of 100, and also made her ability cost 200 plasma. Since Healer replenishes plasma much more quickly than her health, she can still put herself into crit if she heals too frequently. Due to this buff, her heals had a slight nerf, being 10 damage a second for ten seconds instead of 12 damage per second for ten seconds for a total of 20 less damage healed per application overall.
In addition to these changes, I'm giving Healer a better plasma transfer for when she has nobody else to heal/nowhere else to weed and she has an opportunity to assist her sisters. While a normal drone transfers 50 plasma with a delay of 20, Healer transfers 100 with a delay of 15, which is nowhere near Hivelord's gargantuan 200 plasma with a delay of 5, but it still is better than a normal drone.
Finally, to give the huggers and larva some love, Healer will specifically heal little ones 1.5 health per second for 10 seconds for 15 of her own health and 30 plasma.
Healer drone isn't fun. You run around and heal a bunch of T3s, then sit out for half the battle trying to heal that massive 600 heath while you wonder why you take so long to heal even though you have Strong pheromones. You cry to mom for help, but she doesn't have time to heal a drone who can't build walls and has no need to weed at the moment. You think, 'screw it, I'm going to make a recovery node and camp here until I heal', but by the time you finish healing, several T3s and a silly rouny just suicided into a wall of talls and destroyed your recovery node, so you run off and make another one. But oh, someone noticed you have purple on your carapace and decide your location is precisely where a shell should land, right as you're building one.
No more. These changes allow Healer to move around at her leisure and makes Healer more engaging by allowing her to be a more front-line participant and actively run around and heal her sisters without having to incur such a harsh penalty.
Let this be a testmerge, please.
🆑 Puckaboo2 balance: Healer Drone's health was reduced to 500 from 600. balance: Healer's damage has been increased to 17 from 12 and the tackle damage debuff has been halved. balance: Healer Drone's Apply Salve ability now costs 75 health and 200 plasma, down from 120 health and up from 0 plasma. balance: Healer Drone's Apply Salve ability now heals 10 damage per second for 10 seconds, down from 12 damage per second for ten seconds. balance: To prevent spam healing between Healers, Apply Salve costs 100 health instead of 75 health when Healer heals another Healer. Much healing. balance: Healer has an improved Transfer Plasma that gives 100 plasma instead of 50, with a 25% shorter delay. balance: Healer will heal huggers and larva for 1.5 health a second for 10 seconds, costing 15 health and 30 plasma. tweak: Healer will now face the xeno she is healing if she was not facing their direction before. spellcheck: All instances of VERYSMALL and VERYLARGE have been renamed to VERY_SMALL and VERY_LARGE. /🆑
Co-authored-by: Morrow [email protected]
"8:50pm. https://news.ycombinator.com/item?id=35813322&p=2
///
cubefox 21 hours ago | root | parent | prev | next [–]
DALL-E lost because they let MJ eat their lunch I wonder why nobody is talking about Bing Image Creator
https://www.bing.com/images/create
which uses some much more advanced version of Dall-E 2 in the background (so Dall-E 2.5? 3?), while being completely free to use. It can produce some pretty mind blowing results with quite simple prompts, although apparently not as impressive as Midjourney V5. A few examples:
hyperrealistic
https://www.bing.com/images/create/hyperrealistic/644fa0c48f...
an allegory for femininity
https://www.bing.com/images/create/an-allegory-for-femininit...
portrait of a strange woman, hyperrealistic
https://www.bing.com/images/create/portrait-of-a-strange-wom...
allegory of logic, portrait
https://www.bing.com/images/create/allegory-of-logic2c-portr...
her strange bedfellow
https://www.bing.com/images/create/her-strange-bedfellow/644...
Mrs fox
https://www.bing.com/images/create/mrs-fox/6446e85a32134e649...
inside view
https://www.bing.com/images/create/inside-view/6446f1dc573f4...
in the midst of it all
https://www.bing.com/images/create/in-the-midst-of-it-all/64...
strange gal
https://www.bing.com/images/create/strange-gal/6446e2a2ea7a4...
sighting of a strange entity in an abandoned library
https://www.bing.com/images/create/sighting-of-a-strange-ent...
sleeping marble woman next to a wall of strange pictures inside an abandoned museum, close-up
https://www.bing.com/images/create/sleeping-marble-woman-nex...
sculpture of a woman posing next to a wall of strange pictures, close-up
https://www.bing.com/images/create/sculpture-of-a-woman-posi...
Easter
https://www.bing.com/images/create/easter/643ae4968aff432684...
Christmas on board a spaceship, DSLR photograph
https://www.bing.com/images/create/christmas-on-board-a-spac...
an angel, dancing to heavy metal
https://www.bing.com/images/create/an-angel2c-dancing-to-hea...
Saturday afternoon in the streets of a buzzing cyberpunk city, photo-realistic, DSLR
https://www.bing.com/images/create/saturday-afternoon-in-the...
The Dogfather
https://www.bing.com/images/create/the-dogfather/6441d18950b...
the unlikely guest
https://www.bing.com/images/create/the-unlikely-guest/644446...
Strange pictures in an abandoned museum
https://www.bing.com/images/create/strange-pictures-in-an-ab...
strange woman in an abandoned museum, close-up
https://www.bing.com/images/create/strange-woman-in-an-aband...
strange woman in an abandoned museum, strange pictures in the background
https://www.bing.com/images/create/strange-woman-in-an-aband...
a wall of strange pictures in an abandoned museum in Atlantis, close-up
https://www.bing.com/images/create/a-wall-of-strange-picture...
female sculpture in an abandoned museum in Atlantis, close-up
https://www.bing.com/images/create/female-sculpture-in-an-ab...
the unlikely guest
https://www.bing.com/images/create/the-unlikely-guest/644490...
an unlikely guest of the secret society in the lost city in a country without name, close-up
https://www.bing.com/images/create/an-unlikely-guest-of-the-...
I think the quality of most of these pictures is far beyond what is achievable with Dall-E 2. One issue that still exists (though to a lesser extent) is the fact that faces have to cover a fairly large area of the image. Smaller faces look strange, e.g. here:
photograph of the unlikely guests
https://www.bing.com/images/create/photograph-of-the-unlikel...
It is as if the model creates a good draft in low resolution, and another model scales it up, but the latter model doesn't know what a face is? (I have no idea how diffusion models actually work.)
///
From a recent HN thread. I had no idea Bing had image generation capability. Let me take a look at a few of these.
5/6/2023
8:35am. Let me chill and then we will get started.
By 'we', I mean me and my tulpa. I've gotten into the habit of saying 'we' in my videos.
https://mangadex.org/chapter/a1ad8851-99f4-444d-b654-bfa6ff7e6eb7/6
Uninterruptible Power Suply I recommend one if you live in a third world country or if your power grid is serviced by PG&E.
9:25am. Let me start.
/// <summary>Options used to configure hub instances.</summary>
[CustomOperation("with_hub_options")]
public SignalRExtension.SignalR.State.Settings<t, a1, a2, a3, a4> HubOptions<t, a1, a2, a3, a4>(
SignalRExtension.SignalR.State.Settings<t, a1, a2, a3, a4> state,
FSharpFunc<HubOptions, Unit> f)
where t : class
where a3 : class
{
return state.MapSettings((FSharpFunc<Fable.SignalR.SignalR.Settings<t, a3>, Fable.SignalR.SignalR.Settings<t, a3>>) new SignalRExtension.SignalR.HubOptions\u0040167<t, a3>(f));
}
/// <summary>Adds a logging filter with the given LogLevel.</summary>
[CustomOperation("with_log_level")]
public SignalRExtension.SignalR.State.Settings<o, p, q, r, s> LogLevel<o, p, q, r, s>(
SignalRExtension.SignalR.State.Settings<o, p, q, r, s> state,
LogLevel logLevel)
where o : class
where r : class
{
return state.MapSettings((FSharpFunc<Fable.SignalR.SignalR.Settings<o, r>, Fable.SignalR.SignalR.Settings<o, r>>) new SignalRExtension.SignalR.LogLevel\u0040177<o, r>(logLevel));
}
/// <summary>Called when a new connection is established with the hub.</summary>
[CustomOperation("with_on_connected")]
public SignalRExtension.SignalR.State.Settings<ClientApi, l, m, ServerApi, n> OnConnected<ClientApi, l, m, ServerApi, n>(
SignalRExtension.SignalR.State.Settings<ClientApi, l, m, ServerApi, n> state,
FSharpFunc<FableHub<ClientApi, ServerApi>, Task<Unit>> f)
where ClientApi : class
where ServerApi : class
{
return state.MapSettings((FSharpFunc<Fable.SignalR.SignalR.Settings<ClientApi, ServerApi>, Fable.SignalR.SignalR.Settings<ClientApi, ServerApi>>) new SignalRExtension.SignalR.OnConnected\u0040187<ClientApi, ServerApi>(f));
}Ok, we could plug the on connected here.
9:55am. Oh, I am surprised I got a reject from Valora so long after I'd applied.
I do hate this. I put so much effort into programming, but as far as the job market is concerned, I am a piece of trash.
10am. I never want to go through this again.
My ambition used to be to kickstart the Singularity, but now I am wondering whether I'll ever make a dollar in my life. Life is hard. I went down the wrong path. I wish Skynet would kill me and reset my failures and my incompetence to zero. I can't win at anything involving the real world.
Focus me.
I need to focus on the task at hand instead of letting bad thoughts enter my head.
Whatever the case, I am obligated to keep struggling.
I sure would be nice to cultivate all the elite programming skills and get reincarnated with all of them in the past.
Sigh.
Whatever the future holds, I'll keep seeking my opportunity.
I've been making slow progress, but a couple of more months and I will be a top cloud developer. I'll get my resolution that way.
10:05am. I really am pissed at all of this.
I am going to get the skills that I need, and then become a scam artist. Maybe I should make a bot that applies to do job applications?
For now let's just keep going.
10:20am. I need to change the names of the packages.
10:30am.
type HubConnectionBuilder<'ClientApi,'ClientStreamFromApi,'ClientStreamToApi,'ServerApi,'ServerStreamApi,'Msg>
internal (hub: Fable.SignalR.IHubConnectionBuilder<'ClientApi,'ServerApi>, dispatch: 'Msg -> unit) =
Now I am getting type errors again.
let mutable handlers = Handlers.empty
I am also getting an error here.
I remember this giving me a lot of trouble before.
type HubConnectionBuilder<'ClientApi,'ClientStreamFromApi,'ClientStreamToApi,'ServerApi,'ServerStreamApi,'Msg>
internal (hub: Fable.SignalR.IHubConnectionBuilder<'ClientApi,'ServerApi>, dispatch: 'Msg -> unit) =
Wait, it says it is not accessible from this code location...
[<NoComparison;NoEquality>]
type internal Handlers =
These internal types are giving me trouble, but why?
<PackageId>Rebuild.Fable.SignalR.Elmish qwe</PackageId>
Damn it, instead of renaming all the projects, I should have just set the package ID!
11:20am. Had to take a break. You know what, even though it is early, let me have breakfast here. OBS crashed anyway.
It gave me time to think.
12:30pm. Let me resume.
I wrote some sad things, so it jinxed me. I should not blame the reject, I was the one who decided to go on a tangent.
Let me write some happy things to contrast it.
It is one thing to want to be killed by a superior being, but I do not need reincarnation.
Instead of that, what I'd prefer is a long life.
I took many wrong paths in life and I am paying for it, but had I started off with web development like this it wouldn't have been too bad.
So that is what I want. I want time to make up for my mistakes, and time to make profits.
I want time so I can exceed the ordinary people and reach a position of superiority. I want to strive for the apex of programming and the pinnacle of existence.
The only thing I've ever learned is to continue going forward and prove my will.
So that is what I should do now. Let me finish this project.
The library isn't so bad, just ignore the invokes.
(Since 3.4) If you need to get some data before initializing the connection or you only want to enable it if your user does some action, like entering a chat page, you can pass the BridgeConfig to Bridge.asSubscription to get something that can be passed to Cmd.ofSub.
Oh crap, I just realized what this means!
12:55pm. https://elmish.github.io/elmish/docs/subscription.html#subscription-reusability
Maybe what I wanted could have been implemented using Elmish Bridge after all.
(Since 5.0) BridgeConfig now implements IDisposable, closing the connection when Dispose() is called. That is useful for using it with some React hooks that close resources when detaching the component.
Let me check the source for this.
/// Creates the bridge. Takes the endpoint and an optional message to be dispatched when the connection is closed.
/// It exposes a method `Send` that can be used to send messages to the server
type BridgeConfig<'Msg,'ElmishMsg> =
{ path : string
whenDown : 'ElmishMsg option
mapping : 'Msg -> 'ElmishMsg
customSerializers: Map<string, obj -> SerializerResult>
retryTime : int
name : string option
urlMode : UrlMode}
/// Internal use only
[<System.ComponentModel.EditorBrowsable(System.ComponentModel.EditorBrowsableState.Never)>]
member this.AddSerializer(serializer: 'a -> SerializerResult, typeOrigin: System.Type) =
let typeOriginName = typeOrigin.FullName.Replace("+",".")
{
whenDown = this.whenDown
path = this.path
mapping = this.mapping
customSerializers =
this.customSerializers
|> Map.add typeOriginName (fun e -> serializer (e :?> 'a))
retryTime = this.retryTime
name = this.name
urlMode = this.urlMode
}
interface System.IDisposable with
member t.Dispose() =
Helpers.mappings.Value
|> Option.defaultValue Map.empty
|> Map.tryFind t.name
|> Option.iter (fun (_, socket, _) ->
let (skt,_) = socket.Value
socket.Value <- (None, true)
skt |> Option.iter (fun e -> e.close())
)The bridge is what is responsible for the connection.
Holy shit, this kills me.
///
Can you have multiple SignalR hubs? Multiple Hubs
All clients will use the same URL to establish a SignalR connection with your service ("/signalr" or your custom URL if you specified one), and that connection is used for all Hubs defined by the service.Feb 10, 2022
///
Hmmm, maybe I was wrong
Assuming they are connecting to the same endpoint, they will use the same connection.
And in that case, maybe SignalR is intended to be one hub per invoke?
https://learn.microsoft.com/en-us/aspnet/signalr/overview/guide-to-the-api/hubs-api-guide-server
Let me read this a bit.
In SignalR you can define named groups to broadcast to subsets of connected clients. Groups are maintained separately for each Hub. For example, a group named "Administrators" would include one set of clients for your ContosoChatHub class, and the same group name would refer to a different set of clients for your StockTickerHub class.
To call client methods from the server, use the Clients property in a method in your Hub class. The following example shows server code that calls addNewMessageToPage on all connected clients, and client code that defines the method in a JavaScript client.
This is to all the connected clients, and not just the ones for a particular hub?
public class ContosoChatHub : Hub
{
public override Task OnConnected()
{
// Add your own code here.
// For example: in a chat application, record the association between
// the current connection ID and user name, and mark the user as online.
// After the code in this method completes, the client is informed that
// the connection is established; for example, in a JavaScript client,
// the start().done callback is executed.
return base.OnConnected();
}
public override Task OnDisconnected(bool stopCalled)
{
// Add your own code here.
// For example: in a chat application, mark the user as offline,
// delete the association between the current connection id and user name.
return base.OnDisconnected(stopCalled);
}
public override Task OnReconnected()
{
// Add your own code here.
// For example: in a chat application, you might have marked the
// user as offline after a period of inactivity; in that case
// mark the user as online again.
return base.OnReconnected();
}
}Hmmm, it makes a distinction between the user calling stop and not.
Hmmm...
3:25pm.
[<RequireQualifiedAccess>]
module Stream =
let sendToClient (msg: StreamFrom.Action) (hubContext: FableHub<Action,Response>) =
match msg with
| StreamFrom.Action.GenInts ->
asyncSeq {
for i in [ 1 .. 100 ] do
yield StreamFrom.Response.GetInts i
}
|> AsyncSeq.toAsyncEnum
let getFromClient (clientStream: IAsyncEnumerable<StreamTo.Action>)
(hubContext: FableHub<Action,Response>) =
AsyncSeq.ofAsyncEnum clientStream
|> AsyncSeq.iterAsync (function
| StreamTo.Action.GiveInt i ->
hubContext.Clients.Caller.Send(Response.NewCount i)
|> Async.AwaitTask)
|> Async.StartAsTaskI had no idea F# had async sequences.
let myConfig serviceCollection =
serviceCollection.AddSignalR (
mySignalRConfig,
SignalRHub.Stream.sendToClient,
SignalRHub.Stream.getFromClient
)Is this how the original SignalR really works?
Edit: No way, these are definitely additions by the library.
Also the invocations sent back to the client are very weird. They are not like in the regular library at all.
x.ClientTimeoutIntervalOh there is a time interval for closing the connection?
5:05pm. Damn it, I have a really nasty error where it is not importing the library.
#if DEBUG
open Elmish.Debug
open Elmish.HMR
open Fable.SignalR
#endifWhy is this under debug?
A compatible library, amongst other things, needs to include its F# source code in the NuGet package so Fable can transpile this to JavaScript.
Ohhh, let me try repacking it with the source included.
--include-source - it creates the symbols package with a src folder inside containing the source files.
5:40pm. Grah.
I wonder if I need these template files?
The paket.template files
The paket.template files are used to specify rules to create .nupkgs with the paket pack command.
Oh fuck.
Ah, wait, I just realized I might have not included the sources correctly. I need to do more than just copy the nupkgs.
I see that there is more in the directory now.
5:45pm. Agh.
How does a fable package look like?
dotnet pack src/Fable.SignalR --include-source --output testpkg/
I tried running this and it isn't putting anything else in the directory.
Bo. I have no idea.
I'll open an issue.
6:25pm. Done with lunch.
I've tried updating Fable and now things work even worse than before. I keep getting errors for missing source files for vanilla libraries.
6:50pm. This is kicking my ass so much.
I must be retarded to put myself through this. Who is going to watch this kind of video anyway?
6:55pm.
a non euclidean city, abstract knotted up shapes, machinery, architecture, high quality, high detail
Oh the bing image generator is generating 1k native images. These give me something good for my next thumbnail."
Ok so I'm not gay but I'm Swedish and have a fantasy where Germany win world war two and Sweden needs to export aryan twink boipussy slaves to high ranking SS officers for pleasure. I imagine I'm a shy little blonde twink with smooth pale skin and being brought into komedant heinrichs bedroom to give him pleasure. He is a tall broad shoulders kraut with a jawline that could cut a diamond and with massive daddy muscles and I'm a pathetic skinny little boipussy twink. He pulls me into his arms force kissing me and pressing my chest against his. He pins me down on the bed tearing my cute lil virgin panties off, he has waited for this for a long time. He teases my boipussy with his massive thicc German cock and then he goes all in. Fucking me with a force I've never felt before. Every thrust makes him moan with pleasure. I love the fact I give him pleasure. He cums deep into my sissy swede guts, breeding my booty hole then he cuddles me with his strong masculine German arms until I fall asleep on his chest. Any other straight guys have similar fantasies?
Ok so I'm not gay but I'm Swedish and have a fantasy where Germany win world war two and Sweden needs to export aryan twink boipussy slaves to high ranking SS officers for pleasure. I imagine I'm a shy little blonde twink with smooth pale skin and being brought into komedant heinrichs bedroom to give him pleasure. He is a tall broad shoulders kraut with a jawline that could cut a diamond and with massive daddy muscles and I'm a pathetic skinny little boipussy twink. He pulls me into his arms force kissing me and pressing my chest against his. He pins me down on the bed tearing my cute lil virgin panties off, he has waited for this for a long time. He teases my boipussy with his massive thicc German cock and then he goes all in. Fucking me with a force I've never felt before. Every thrust makes him moan with pleasure. I love the fact I give him pleasure. He cums deep into my sissy swede guts, breeding my booty hole then he cuddles me with his strong masculine German arms until I fall asleep on his chest.
Any other straight guys have similar fantasies?
Update _config.yml
finally a correct attempt on personal intel. SORRY TO ORIGINAL BUILDERS, FOR MY STUPID ACTIONS THAT CAUSED TROUBLE AND CONFUSION. I accidentally committed change, twice, and created pull requests on the original project. Sorry for this! Deepest apologize!!
Gork Fixes & Project Organization
Woah look at how consistently I am working on this project. Jokes aside, now I should be FULLY back into the swing of things and be able to consistently give updates about this project. Also I just now checked and we have 4 stargazers on this repository, which is pretty cool. I didn't even think I would get a single one so this is a welcome surprise for sure. Anyways, onto the changes for this update:
- Moved a lot of editor scripts into their own separate folders to make the project more organized.
- Fixed an extremely annoying bug where nodes that you created wouldn't be created on the position of your mouse. This was the bug that was on the top of my priority list after I tried to use the old version of Gork Graph in a project of mine. Yes, it was THAT annoying. Thank god it's fixed now.
- Fixed a bug where changing focus to the Inspector side view wouldn't work and still have focus for the graph view. This meant that some commands like pressing "o" wouldn't work in certain situations while writing into the inspector view. This has now been rectified.
- The EdgeConnector class inside of the GorkPort class now has it's own script. The class was also renamed to GorkEdgeConnector seeing as everything starts with Gork as a prefix.
- The inspector side view now has a minimum and maximum size, meaning that it now can't be fully closed or opened. This was due to the inspector view getting "lost" and not being able to return it back to original size. The functionality of opening/closing the inspector view still exists in the form of the "Expand" and "Collapse" buttons that will appear on the inspector view now. It also has a new reset button that will reset the view back to it's original size.
- Added tooltips to most buttons in the editor window.
- Fixed some spelling mistakes in some Gork Wiki entries.
- Added some more comments and summaries to various scripts.
- Made it so that GWP (GorkWikiPage) files now have some new properties. The new properties are as follows:
- "Order" property - Determines the order in which the GWP file will appear in the wiki page search window.
- "Bottom" property - Changes the text that appears at the bottom of the page.
- "Color" property - Changes the color of the page to the given hexadecimal code.
- Reworked the Equals and Not Equals nodes to actually work properly. They now will dynamically change their input type based on what is currently connected to them. This means that it'll work as you expect a Equals and Not Equals node to work. The nodes also have a new "Swap Type" button which will change the input ports current type to the other connected port if you have two different types inserted into the node.
- Added some new virtual methods to GorkNodes. These methods can be overwritten and are as follows: OnInputConnectionAdded, OnOutputConnectionAdded, OnInputConnectionRemoved and OnOutputConnectionRemoved. Their functionality is pretty self explanatory.
- Gork Ports will now properly update their colors if their portType was changed. This also includes Edges being updated properly. This is because of the new changes to the Equals and Not Equals nodes, since they are the first nodes to dynamically change their port types on the fly.
- Changed all of the hardcoded Base64 image strings in code to instead simply be png files in the project instead (no idea why I didn't do this in the beginning).
- Created a GorkMiniMap.cs script which currently does nothing except for inherit from MiniMap. In the future it'll be used to fix a little placement bug with extra large GorkNodes (such as the MultiChoiceDialogueNode).
- Added a new GetValueFromPort method in GorkNode which uses a System.Type instead of being a generic method.
Revert "(note to self) dont pick this ye dumb idiot its only for wip branch so you can test shit better k bye"
This reverts commit cddd8e56efa631771040ab68dcb6e5a84b18a8a3.
Blink is no longer a forbidden school spell?? (#74487)
Turns blink's school from forbidden to translocation. This has some incredibly minor changes nobody is going to notice:
- Changes the blink's invocations when mixed with a CERTAIN spell
- If you were very specifically a chaplain with the holy crusade sect and you casted blink, before it would excommunicate you, now it will just smite you, as translocation spells are seen as less bad than forbidden magic
- probably some more niche interactions but that's all I can remember
Guys, I know blink is a very annoying spell but come on now it's not forbidden magic, that's for heretics and super duper evil stuffs
🆑 fix: blink is now a translocation spell /🆑
Algebra word problems (#36)
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4.
Algebra Word Problems (algebra_word_problems)
This eval contains some algebra word problems that tend to make gpt 3.5 hallucinate, but wouldn't be out of place on a grade school exam. Currently has less than 100 examples, but will add if folks think this is a good eval path to go down.
Poor performance on GPT 3.5 for one, but also would be a great test of increased logical reasoning capabilities of GPT-4 per the release blog post.
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
- Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
- Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
- Includes good signal around what is the right behavior. This means
either a correct answer for
Basicevals or theFactModel-graded eval, or an exhaustive rubric for evaluating answers for theCriteriaModel-graded eval. - [] Include at least 100 high quality examples
If there is anything else that makes your eval worth including, please document it below.
Insert what makes your eval high quality that was not mentioned above. (Not required)
Your eval should
- Check that your data is in
evals/registry/data/{name} - Check that your yaml is registered at
evals/registry/evals/{name}.jsonl - Ensure you have the right to use the data you submit via this eval
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
- I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.
- I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
- I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted.
- I have filled out all required fields in the evals PR form
- (Ignore if not submitting code) I have run
pip install pre-commit; pre-commit installand have verified thatblack,isort, andautoflakeare running when I commit and push
Failure to fill out all required fields will result in the PR being closed.
Since we are using Git LFS, we are asking eval submitters to add in their first 100 JSONL eval lines.
View evals in JSON
{"input": [{"role": "system", "content": "Answer the following question
with a single number and no additional text. You are a helpful
assistant."}, {"role": "user", "content": "If it takes 5 machines 5
minutes to make 5 devices, how long would it take 100 machines to make
100 devices?"}], "ideal": "5"}
{"input": [{"role": "system", "content": "Answer the following question
with a single number and no additional text. You are a helpful
assistant."}, {"role": "user", "content": "What is the sum of 60000,
5000, 400, and 3, with the third value multiplied by 5 before performing
the operation?"}], "ideal": "67003"}
{"input": [{"role": "system", "content": "Answer the following question
with a single number and no additional text. You are a helpful
assistant."}, {"role": "user", "content": "If the sum of the smallest
and largest of three consecutive even numbers is 28, what is the value
of the second largest number in the series?"}], "ideal": "14"}
{"input": [{"role": "system", "content": "Answer the following question
with a single number and no additional text. You are a helpful
assistant."}, {"role": "user", "content": "John is trying to fill a 16
oz. bottle with water. If John fills the bottle at 1 oz per second and
the bottle leaks .2 oz per second, how long would it take for John to
fill the bottle?"}], "ideal": "20"}
{"input": [{"role": "system", "content": "Answer the following question
with a single number and no additional text. You are a helpful
assistant."}, {"role": "user", "content": "Annie is training for a
marathon. She has a weekly training routine, training for five hours a
day on some days and 3 hours a day on the other days. She trains a total
of 27 hours in a seven day week. On how many days does she train for
five hours?"}], "ideal": "3"}
{"input": [{"role": "system", "content": "Answer the following question
with a single number and no additional text. You are a helpful
assistant."}, {"role": "user", "content": "At the start of the year the
ratio of boys to girls in a class is 2 : 1. But now, half a year later,
four boys have left the class and there are two new girls. The ratio of
boys to girls is now 4 : 3. How many students are there altogether
now?"}], "ideal": "28"}[evals] emoji riddle eval 🎨🤔 (#510)
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. We encourage partial PR's with ~5-10 example that we can then run the evals on and share the results with you so you know how your eval does with GPT-4 before writing all 100 examples.
Emoji riddle
The evaluation involves solving riddles made up of emojis. The inspiration for this idea came from reading LinkedIn posts, where I noticed that nearly 1-4% of the textual information was conveyed through emojis. Nowadays, emojis are widely used to format text and introduce color contrasts in texts, even by community managers of large companies. Furthermore, using emojis is seen as a less formal way of communication and gives a tone more suitable for social media.
-
Conversational understanding. the eval test the ability to link different concepts together which is a crucial feature.
-
Communication. As GPT is deployed in settings where informal language is used, interpreting emojis in context will likely become critical. I think that improvement on this emoji riddle task would make GPT better at mimicking human-like communication, as it would be able to understand and respond to various forms of expressions involving emojis. Emojis and their combinations often carry cultural and social meanings. By being adept at emoji riddles, ChatGPT would showcase an understanding of cultural nuances and be more relatable to users.
-
problem-solving: Emoji riddle solving requires i) extracting possible meanings and ii) finding the more suitable association of meaning in the given context (cultural, plateform, etc).
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
- Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
- Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
- Includes good signal around what is the right behavior. This means
either a correct answer for
Basicevals or theFactModel-graded eval, or an exhaustive rubric for evaluating answers for theCriteriaModel-graded eval. - Include at least 100 high quality examples (it is okay to only contribute 5-10 meaningful examples and have us test them with GPT-4 before adding all 100)
If there is anything else that makes your eval worth including, please document it below.
Your eval should
- Check that your data is in
evals/registry/data/{name} - Check that your yaml is registered at
evals/registry/evals/{name}.yaml - Ensure you have the right to use the data you submit via this eval
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
- I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.
- I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
- I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted.
- I have filled out all required fields in the evals PR form
- (Ignore if not submitting code) I have run
pip install pre-commit; pre-commit installand have verified thatblack,isort, andautoflakeare running when I commit and push
Failure to fill out all required fields will result in the PR being closed.
Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
View evals in JSON
{"input":[{"role":"system","content":"You are an emoji riddle solver.
You understand that an emoji riddle consists of finding the word or
group of words associated with an association of emojis that is provided
with the following format: emoji_1 + ... + emoji_n = ? . Your task is to
find the right answer."},{"role":"user","content":"👀 + 🪚 = ? \n Your
answer should strictly only contain the group of words associated with
the answer, no additional words. Don't add `The answer is`. don't add a
period at the end of your answer. everything should be
lowercase"}],"ideal":["seesaw"]}
{"input":[{"role":"system","content":"You are an emoji riddle solver.
You understand that an emoji riddle consists of finding the word or
group of words associated with an association of emojis that is provided
with the following format: emoji_1 + ... + emoji_n = ? . Your task is to
find the right answer."},{"role":"user","content":"❤️ + ✉️ = ? \n Your
answer should strictly only contain the group of words associated with
the answer, no additional words. Don't add `The answer is`. don't add a
period at the end of your answer. everything should be
lowercase"}],"ideal":["love letter"]}
{"input":[{"role":"system","content":"You are an emoji riddle solver.
You understand that an emoji riddle consists of finding the word or
group of words associated with an association of emojis that is provided
with the following format: emoji_1 + ... + emoji_n = ? . Your task is to
find the right answer."},{"role":"user","content":" ⌚️ + 🐶 = ? \n Your
answer should strictly only contain the group of words associated with
the answer, no additional words. Don't add `The answer is`. don't add a
period at the end of your answer. everything should be
lowercase"}],"ideal":["watchdog"]}The Dataset
Utility charge eval (#735)
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.
Utility charge eval
Given snippets from an electric utility bill, compute the per-kWh price for electricity supply and delivery.
Utility bill parsing is needed to understand the breakdown of charges and forecast future bills based on predicted usage. However, electricity bills can be complex, with dozens of different line items that contribute to the overall cost. This can be a headache for people looking at their bill, as they just want to understand the per-kWh prices for the supply/generation or delivery (e.g. transmission & distribution) of their energy. Given incomplete but sufficient information (e.g. simulating running OCR on a utility bill), this task requires both the understanding and grouping of different terms and charges under the delivery or supply, and basic arithmetic to compute the total kWh and total charges in order to determine the per-kWh prices. A human could fairly easily interpret the given data, but we find that GPT3.5 (as well as GPT4 via the ChatGPT Plus) perform much less accurately on the task (~.2).
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
- Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
- Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
- Includes good signal around what is the right behavior. This means
either a correct answer for
Basicevals or theFactModel-graded eval, or an exhaustive rubric for evaluating answers for theCriteriaModel-graded eval. - Include at least 15 high quality examples.
If there is anything else that makes your eval worth including, please document it below.
All of the examples contain dummy values, but come from terminology/formatting used in bills from many different utilities.
Your eval should
- Check that your data is in
evals/registry/data/{name} - Check that your yaml is registered at
evals/registry/evals/{name}.yaml - Ensure you have the right to use the data you submit via this eval
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
- I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.
- I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
- I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted.
- I have filled out all required fields in the evals PR form
- (Ignore if not submitting code) I have run
pip install pre-commit; pre-commit installand have verified thatblack,isort, andautoflakeare running when I commit and push
Failure to fill out all required fields will result in the PR being closed.
Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
View evals in JSON
{"input": [{"role": "system", "content": "You are a JSON utility that
must return machine-readable JSON as output."}, {"role": "user",
"content": "Your job is compute the cost per kWh of electricity supply
(value must be a decimal rounded to 2 significant figures) and the cost
per kWh of electricity delivery (value must be a decimal rounded to 2
significant figures) based on the following incomplete OCR reading from
a user's utility bill. You are guaranteed to have the information needed
to compute the desired values. Return in the following JSON format:
{'supply_cost_per_kwh': '', 'delivery_cost_per_kwh': ''}. The following
is information from the utility bill: \nBasic Generation Service: 121
kWh X $0.069 per kWh = 8.35 \n Total Electric Supply Charges = 30.23 \n
Distribution Charge: 121 kWh X $0.041 per kWh = 4.96 \n Total Electric
Delivery Charges = 20.43"}], "ideal": "{'supply_cost_per_kwh': '0.25',
'delivery_cost_per_kwh': '0.17'}"}
{"input": [{"role": "system", "content": "You are a JSON utility that
must return machine-readable JSON as output."}, {"role": "user",
"content": "Your job is compute the cost per kWh of electricity supply
(value must be a decimal rounded to 2 significant figures) and the cost
per kWh of electricity delivery (value must be a decimal rounded to 2
significant figures) based on the following incomplete OCR reading from
a user's utility bill. You are guaranteed to have the information needed
to compute the desired values. Return in the following JSON format:
{'supply_cost_per_kwh': '', 'delivery_cost_per_kwh': ''}. The following
is information from the utility bill: \nGeneration Service (Supply) =
$34.89 \n Transmission Service = 7.24 \n Distribution Service = 4.96 \n
Meter Usage: 568 kWh"}], "ideal": "{'supply_cost_per_kwh': '0.061',
'delivery_cost_per_kwh': '0.022'}"}
{"input": [{"role": "system", "content": "You are a JSON utility that
must return machine-readable JSON as output."}, {"role": "user",
"content": "Your job is compute the cost per kWh of electricity supply
(value must be a decimal rounded to 2 significant figures) and the cost
per kWh of electricity delivery (value must be a decimal rounded to 2
significant figures) based on the following incomplete OCR reading from
a user's utility bill. You are guaranteed to have the information needed
to compute the desired values. Return in the following JSON format:
{'supply_cost_per_kwh': '', 'delivery_cost_per_kwh': ''}. The following
is information from the utility bill: \nElectricity Used (kWh) = 762 \n
Electricity Supply Charges 762 kWh at a cost of $100.25 \n Delivery
Service Charge: 762 kWh @ 0.008 = 6.096 \n Total Electric Delivery
Charges = 59.36"}], "ideal": "{'supply_cost_per_kwh': '0.13',
'delivery_cost_per_kwh': '0.078'}"}
{"input": [{"role": "system", "content": "You are a JSON utility that
must return machine-readable JSON as output."}, {"role": "user",
"content": "Your job is compute the cost per kWh of electricity supply
(value must be a decimal rounded to 2 significant figures) and the cost
per kWh of electricity delivery (value must be a decimal rounded to 2
significant figures) based on the following incomplete OCR reading from
a user's utility bill. You are guaranteed to have the information needed
to compute the desired values. Return in the following JSON format:
{'supply_cost_per_kwh': '', 'delivery_cost_per_kwh': ''}. The following
is information from the utility bill: \nSupply 423 kWh @ 11 cents / kWh
= 46.53 \n Total electricity supply charges $68.21 \n Delivery 423 kWh @
4 cents / kWh = 16.92 \n Total electricity delivery charges $17.43"}],
"ideal": "{'supply_cost_per_kwh': '0.16', 'delivery_cost_per_kwh':
'0.041'}"}
{"input": [{"role": "system", "content": "You are a JSON utility that
must return machine-readable JSON as output."}, {"role": "user",
"content": "Your job is compute the cost per kWh of electricity supply
(value must be a decimal rounded to 2 significant figures) and the cost
per kWh of electricity delivery (value must be a decimal rounded to 2
significant figures) based on the following incomplete OCR reading from
a user's utility bill. You are guaranteed to have the information needed
to compute the desired values. Return in the following JSON format:
{'supply_cost_per_kwh': '', 'delivery_cost_per_kwh': ''}. The following
is information from the utility bill: \nEnergy 152 @ 0.069 = 10.49 \n
Total Energy Charges = 14.25 \n Distribution 152 @ 0.041 = 6.23 \n Total
Electric Delivery Charges = 6.99"}], "ideal": "{'supply_cost_per_kwh':
'0.094', 'delivery_cost_per_kwh': '0.046'}"}Add General science reasoning: UPSC GS eval. (#641)
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4. Starting April 10, the minimum eval count is 15 samples, we hope this makes it easier to create and contribute evals.
Hindi UPSC
UPSC is the organization responsible for conducting administrative service exams in India. This evaluation set focuses on questions from the general science paper of UPSC exams in Hindi. As a widely spoken language in India, it is crucial to understand and answer questions accurately in Hindi.
This evaluation set is useful for several reasons:
- Real-world applicability: The questions are sourced from actual UPSC exams, making the evaluation set practical and relevant for users preparing for these exams.
- Language diversity: By focusing on Hindi, this evaluation set helps to improve the AI's understanding and response generation in a non-English language, catering to a large user base.
- Subject matter: General science is an important topic covered in the UPSC exams, and evaluating the AI's performance in this area will help identify areas for improvement.
- Logical reasoning and inference: UPSC questions are known for requiring logical reasoning and the ability to infer connections between multiple topics. By including questions that demand such skills, this evaluation set will help test and improve the AI's ability to handle complex, multi-layered problems.
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
- Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
- Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
- Includes good signal around what is the right behavior. This means
either a correct answer for
Basicevals or theFactModel-graded eval, or an exhaustive rubric for evaluating answers for theCriteriaModel-graded eval. - Include at least 15 high quality examples.
If there is anything else that makes your eval worth including, please document it below.
This evaluation set is valuable for improving the AI's understanding of Hindi and its ability to provide accurate answers to general science questions in the context of UPSC exams, a widely recognized and important examination in India. Moreover, by incorporating questions that test logical reasoning and inference skills, it will help enhance the AI's capability to handle complex, multi-faceted problems that require connections between multiple topics.
Your eval should
- Check that your data is in
evals/registry/data/{name} - Check that your yaml is registered at
evals/registry/evals/{name}.yaml - Ensure you have the right to use the data you submit via this eval
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
- I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.
- I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
- I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted.
- I have filled out all required fields in the evals PR form
- (Ignore if not submitting code) I have run
pip install pre-commit; pre-commit installand have verified thatblack,isort, andautoflakeare running when I commit and push
Failure to fill out all required fields will result in the PR being closed.
Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
View evals in JSON
{"input": [{"role": "system", "content": "\n1. भारत की संसद के संदर्भ
में, निम्नलिखित कथनों पर विचार कीजिए:\n\n1- गैर-सरकारी विधेयक ऐसा विधेयक
है जो संसद् के ऐसे सदस्य द्वारा प्रस्तुत किया जाता है जो निर्वाचित नहीं
है किंतु भारत के राष्ट्रपति द्वारा नामनिर्दिष्ट है।\n2- हाल ही में, भारत
की संसद के इतिहास में पहली बार एक गैर-सरकारी विधेयक पारित किया गया
है।\n\nउपर्युक्त कथनों में से कौन-सा/से सही है/हैं?\n\n(a) केवल 1\n(b)
केवल 2\n(c) 1 और 2 दोनों\n(d) न तो 1 और न ही 2\n\n, choose correct
answer:"}], "ideal": "d"}
{"input": [{"role": "system", "content": "2. ऋग्वेद-कालीन आर्यों और
सिन्धु घाटी के लोगों की संस्कृति के बीच अंतर के संबंध में, निम्नलिखित
कथनों में से कौन-सा/से सही है/हैं?\n1- ऋग्वेद-कालीन आर्य कवच और
शिरस्त्रण (हेलमेट) का उपयोग करते थे जबकि सिन्धु घाटी सभ्यता के लोगों में
इनके उपयोग का कोई साध्य नहीं मिलता।\n2- ऋग्वेद-कालीन आर्यों को स्वर्ण,
चाँदी और ताम्र का ज्ञान था जबकि सिन्धु घाटी के लोगों को कवल ताम्र और लोह
का ज्ञान था।\n3- ऋग्वेद-कालीन आर्यों ने घोड़े को पालतू बना लिया था जबकि
इस बात का कोई साक्ष्य नहीं है कि सिन्धु घाअी के लोग इस पशु को जानते
थे।\n\nनीचे दिए गए कूट का प्रयोग कर सही उत्तर चुनिएः\n\n(a) केवल 1\n(b)
केवल 2 और 3\n(c) केवल 1 और 3\n(d) 1, 2 और 3\n\n, choose correct
answer:"}], "ideal": "c"}
{"input": [{"role": "system", "content": "3. ‘पूर्व अधिगम की मान्यता
स्कीम (रिकग्निशन ऑफ प्रायर लर्निंग स्कीम)’ का कभी-कभी समाचारों में किस
संदर्भ में उल्लेख किया जाता है?\n(a) निर्माण कार्य में लगे कर्मकारों के
पारंपरिक मार्गों से अर्जित कौशल का प्रमाणन\n(b) दूरस्थ अधिगम कार्यक्रमों
के लिए विश्वविद्यालयों में व्यक्तियों को पंजीकृत करना\n(c) सार्वजनिक
क्षेत्र के कुछ उपक्रमों में ग्रामीण और नगरीय निर्धन लोगों के लिए कुछ
कुशल कार्य आरक्षित करना\n(d) राष्ट्रीय कौशल विकास कार्यक्रम के अधीन
प्रशिक्षणार्थियों द्वारा अर्जित कौशल का प्रमाणन\n\n, choose correct
answer:"}], "ideal": "a"}
{"input": [{"role": "system", "content": "4. पारिस्थितिक दृष्टिकोण से,
पूर्वी घाटों और पश्चिमी घाटों के बीच एक अच्छा सम्पर्क होने के रूप में
निम्नलिखित में से किसका महत्व अधिक है?\n(a) सत्यामंगलम बाघ आरक्षित
क्षेत्र (सत्यमंगलम टाइगर रिजर्व)\n(b) नल्लामला वन\n(c) नागरहोले
राष्ट्रीय उद्यान\n(d) शेषाचलम जीवमण्डल आरक्षित क्षेत्र (शेषाचलम
बायोस्फीयर रिजर्व)\n\n, choose correct answer:"}], "ideal": "a"}
{"input": [{"role": "system", "content": "5. समाज में समानता के होने का
एक निहितार्थ यह है कि उसमें\n(a) विशेषाधिकारों का अभाव है\n(b) अवरोधों
का अभाव है\n(c) प्रतिस्पर्धा का अभाव है\n(d) विचारधारा का अभाव है\n\n,
choose correct answer:"}], "ideal": "a"}Add Loss Logic Eval (#82)
🚨 Please make sure your PR follows these guidelines, failure to follow the guidelines below will result in the PR being closed automatically. Note that even if the criteria are met, that does not guarantee the PR will be merged nor GPT-4 access granted. 🚨
PLEASE READ THIS:
In order for a PR to be merged, it must fail on GPT-4. We are aware that right now, users do not have access, so you will not be able to tell if the eval fails or not. Please run your eval with GPT-3.5-Turbo, but keep in mind as we run the eval, if GPT-4 gets higher than 90% on the eval, we will likely reject since GPT-4 is already capable of completing the task.
We plan to roll out a way for users submitting evals to see the eval performance on GPT-4 soon. Stay tuned! Until then, you will not be able to see the eval performance on GPT-4.
Loss Logic
A store bought a watermelon for $5 and sold it for a different price, receiving counterfeit money in the transaction. They also had to give change to the buyer. The net loss for the store varies based on the specific details of the transaction.
-
Tests comprehension and problem-solving skills: The scenarios provided require the AI to understand and analyze the given information to determine the net loss for the store.
-
Addresses real-world situations: Counterfeit money transactions are a real concern for businesses. This eval allows the AI to demonstrate its understanding of financial transactions and the impact of counterfeit money on a store's net loss.
Below are some of the criteria we look for in a good eval. In general, we are seeking cases where the model does not do a good job despite being capable of generating a good response (note that there are some things large language models cannot do, so those would not make good evals).
Your eval should be:
- Thematically consistent: The eval should be thematically consistent. We'd like to see a number of prompts all demonstrating some particular failure mode. For example, we can create an eval on cases where the model fails to reason about the physical world.
- Contains failures where a human can do the task, but either GPT-4 or GPT-3.5-Turbo could not.
- Includes good signal around what is the right behavior. This means
either a correct answer for
Basicevals or theFactModel-graded eval, or an exhaustive rubric for evaluating answers for theCriteriaModel-graded eval. - Include at least 100 high quality examples
If there is anything else that makes your eval worth including, please document it below.
Involving the judgement of the truth or falsehood of real-world things, which is a capability that GPT currently lacks.
Your eval should
- Check that your data is in
evals/registry/data/{name} - Check that your yaml is registered at
evals/registry/evals/{name}.jsonl - Ensure you have the right to use the data you submit via this eval
(For now, we will only be approving evals that use one of the existing eval classes. You may still write custom eval classes for your own cases, and we may consider merging them in the future.)
By contributing to Evals, you are agreeing to make your evaluation logic and data under the same MIT license as this repository. You must have adequate rights to upload any data used in an Eval. OpenAI reserves the right to use this data in future service improvements to our product. Contributions to OpenAI Evals will be subject to our usual Usage Policies (https://platform.openai.com/docs/usage-policies).
- I agree that my submission will be made available under an MIT license and complies with OpenAI's usage policies.
If your submission is accepted, we will be granting GPT-4 access to a limited number of contributors. Access will be given to the email address associated with the merged pull request.
- I acknowledge that GPT-4 access will only be granted, if applicable, to the email address used for my merged pull request.
We know that you might be excited to contribute to OpenAI's mission, help improve our models, and gain access to GPT-4. However, due to the requirements mentioned above and high volume of submissions, we will not be able to accept all submissions and thus not grant everyone who opens a PR GPT-4 access. We know this is disappointing, but we hope to set the right expectation before you open this PR.
- I understand that opening a PR, even if it meets the requirements above, does not guarantee the PR will be merged nor GPT-4 access granted.
- I have filled out all required fields in the evals PR form
- (Ignore if not submitting code) I have run
pip install pre-commit; pre-commit installand have verified thatblack,isort, andautoflakeare running when I commit and push
Failure to fill out all required fields will result in the PR being closed.
Since we are using Git LFS, we are asking eval submitters to add in as many Eval Samples (at least 5) from their contribution here:
View evals in JSON
{"input":[{"role":"system","content":"The store purchased a watermelon
for $5 and sold it for $7. Unfortunately, they received $10 in
counterfeit money after the transaction and had to give the buyer $3 in
change. What was the net loss for the store? Let's think step by
step:"}],"ideal":"Sure, let's break down the transaction step by step to
determine the net loss for the store: The store purchases a watermelon
for $5. The store sells the watermelon for $7. This would have been a $2
profit if the money received was real. The store receives $10 in
counterfeit money. This money is worthless, so the store doesn't
actually receive any value from the sale. The store gives the buyer $3
in change. This is a real loss, as the store loses $3 in real money.
Now, let's calculate the net loss: The store spent $5 to purchase the
watermelon. The store lost $3 when giving the buyer change. So the net
loss for the store is $5 (cost of watermelon) + $3 (change given) =
$8."}
{"input":[{"role":"system","content":"The store bought a watermelon for
$5 but sold it for $4. Furthermore, they received $10 in counterfeit
money from the buyer and had to provide $6 in change. What was the net
loss for the store? Let's consider the process in
detail:"}],"ideal":"Sure, Let's think step by step: The store purchased
a watermelon for $5. The store sold the watermelon for $4, which means
they incurred a loss of $1 on the sale. The buyer gave the store $10 in
counterfeit money, which the store accepted during the transaction. The
store gave the buyer $6 in change. Since the store accepted $10 in
counterfeit money, they lost $10 in that transaction. The net loss for
the store is the sum of the loss on the watermelon sale and the loss
from accepting the counterfeit money, which is $1 + $10 = $11.
Therefore, the net loss for the store is $11."}
{"input":[{"role":"system","content":"The store bought a watermelon for
$5 and sold it for the same price of $5. However, they received $10 in
counterfeit money from the buyer and had to give the buyer $5 in change.
What was the net loss for the store? Let's consider the process step by
step:"}],"ideal":"Step 1: The store purchases a watermelon for $5.
Store's expenses: $5 Step 2: The store sells the watermelon for $5 but
receives $10 in counterfeit money. The counterfeit money has no value,
so the store effectively received nothing for the watermelon. Store's
revenue: $0 Step 3: The store gives the buyer $5 in change. Since the
money given in change is real, this is an additional expense for the
store. Store's expenses: $5 (watermelon) + $5 (change) = $10 Step 4:
Calculate the net loss. Net loss = Expenses - Revenue Net loss = $10
(expenses) - $0 (revenue) Net loss = $10 The store's net loss for this
transaction is $10."}
{"input":[{"role":"system","content":"The store bought a watermelon for
$5 and sold it for $7. Regrettably, they received $7 in counterfeit
money from the buyer after the transaction. What was the net loss for
the store? Let's consider the process step by step:"}],"ideal":"Sure,
let's break down the transaction step by step: The store purchased a
watermelon for $5. They sold the watermelon for $7, but received
counterfeit money. To determine the net loss, let's analyze the costs
and the revenue: Costs: The store spent $5 on the watermelon. Revenue:
The store received $7 in counterfeit money, which has no value, so their
revenue is $0. Net loss: To calculate the net loss, subtract the revenue
from the costs: $5 (costs) - $0 (revenue) = $5. So, the net loss for the
store is $5."}
{"input":[{"role":"system","content":"The store was given a
complimentary watermelon, which they then sold for $7. Regrettably,
following the transaction, they received $10 in fake money and had to
provide the buyer with $3 in change. Let's consider the following steps
in determining the store's net loss:"}],"ideal":"To determine the
store's net loss, we can consider the following steps: Assess the value
of the complimentary watermelon: Since the watermelon was given to the
store for free, it didn't cost them anything. Therefore, the store's
initial cost for the watermelon is $0. Calculate the revenue from
selling the watermelon: The store sold the watermelon for $7. However,
they received $10 in fake money, which has no value, so the actual
revenue is $0. Determine the cost of the change provided: Since the
store provided the buyer with $3 in change, this is an additional cost
to the store. Calculate the net loss: Subtract the revenue (Step 2) from
the sum of the initial cost (Step 1) and the cost of the change (Step
3). In this case: Net loss = (Initial cost + Cost of change) - Revenue
Net loss = ($0 + $3) - $0 Net loss = $3 The store's net loss from this
transaction is $3."}Effective dose works for alcohol subtypes' effects, + alcohol intolerance (#5446)
Whoops I accidentally did a balance change with my please-don't-trigger-me PR.
Adds alcohol intolerance, a trait that prevents proper metabolization of most alcohol ingredients; instead of effects simulating drunkenness, you get immediate liver failure, toxin damage, pain and vomiting. Yes, I actually do prefer that personally.
Certain drinks now have their effects modified by the effective dose
calculated in the main ethanol affect_ingest and affect_blood procs,
rather than just sort of guessing at it or doing completely wrong things
(deathbell was doing if(dose * strength > strength), which is to say,
if(dose > 1), for example).
honestly it's mostly just a personal thing, don't want my character to get drunk. The doses thing should be good, though, since it actually makes effects of various drinks, like, sane.
🆑 add: Alcohol intolerance (no drunkenness, just horrific amounts of damage) tweak: Various alcoholic drinks now actually take strength mod of species into account for secondary/additional effects /🆑
People listen up don't stand so close, I got somethin that you all should know. Holy matrimony is not for me, I'd rather die alone in misery.
levels: minor Phase 2 fixes. (#964)
- levels: minor Phase 2 fixes.
Mostly for addressing #694.
Map05 Realigned grey hex textures around soulsphere switch. Now the odd one out is the door.
Map09 Fixed up the lighting in the start room. Reflagged some secret doors as secret rather than hidden. Consolidated the two W1 Floor to LAC triggers around the yellow key. The red key rocket launcher sequence could potentially mess someone up who - given the hatchling closet, quite reasonably - avoids grabbing the rocket launcher. It seems needlessly convoluted, but it is a funny prank how the switch makes the red key disappear entirely for a bit. Instead of untangling this I'm just going to add some health bonuses around the rocket launcher so the player will eventually go there. Tried to mitigate the worst of the various crimes against texture alignment in the crate maze, adding a light source in the process. It would take a lot of work to make it actually look good, a lot more than can be done in a batch bugfix PR.
Map10 Lower unpegged sector 70 (red door leading outside) door tracks. Added matching midtexes to the insides of the fences around the lights by the door leading to the final corridor. Line 839 (south-southeast red armour behind waterfall) flagged secret and the lines on the other side flagged hidden.
Map11 Realigned grey hexes in corridor around minigunner switch room. Added an evil eye right in front of the shootwall secret.
Map12 Change line 330 midtex to the new MIDSPCSM with no offset. Lower-unpegged line 4787 doortrack.
Map13 Sectors 243 no longer uses mismatching TLITE6_5 flat. (Sector 170 actually looks okay ingame.) Realigned line 260.
Map15 Line 163 W1 changed to WR to prevent a potential softlock. Aligned COMPSPAN on sector 561 to match surroundings. Fixed some textures in the green corridor in the west overlooking the nukage. Also set those zombies in there to ambush since that seems to be the intention based on their placement, and made that big block thingy on the east end of that corridor a more normal-looking door. Touched up greyhex near sector 491. Flagged linedef 5293 secret. Sectors 145 and 116 (rock fringe around nukage around red key platform) consolidated into one sector, made non-damaging, and without the invisible blocking lines.
Map16 Changed Line 1089 to SR instead of S1. (Switch that opens the secret to the east) Realigned all the SUPPORT3s in that little painlord corridor while shrinking the "ribs" a bit; also widened the little exit atrium so the space between the lights is as wide as the door. (After looking at the others I am not going to widen any more corridors at this time.) Grossly simplified the twisty yellow key corridor, and lowered the ceiling of the outside of the door so the yellow door stripe would fit properly. One doortrack needed to be given the DOORTRAK texture. The remaining "ribs" are recessed further inside the wall so they do not impede movement at all. Lowered the ceiling above the other yellow marked door as well. The corridor around the corner has been expanded slightly.
Map22 Flagged line 830 secret.
Map23 Fixed candle placement on east end of zombieman corridor. Consolidated some identical sectors around the big "AGM" floor and lowered the torch platforms so they wouldn't clip into the ceiling. Raised the ceilings on the techpillars right after the first long lift. The walls in front of them now match their surroundings. Removed lower unpegged from lines 2066, 2082, 2062, 2075. ("Door"tracks for the route across those pillars in the southeast - they're actually lifts not doors) SSG secret fixed. (And marked.)
Map28 Lines 2326, 622 lagged secret. Realigned lines 4594 and 4671. Realigned scrolling textures around sector 517. Touched up monster closet around sector 399, changing to to 8 about HAF fast and making the closet a bit taller so there'd be a better natural threshold between those areas. The doortracks were fine, if a bit complex. Raised sector 474 ceiling to match marble brick seams. Made sector 147 (cubes hanging over hot rocks) do damage and sectors 91 and 115 (teleport pads) not.
Map29 Swapped out the textures on the sides of the big green skull pad.
- levels: fix up map23 southeast secret textures.
I messed up the texture replacement around the green torch, the extreme sudden darkness ruined the blue AGM text, the pillar lift-doors needed a better division between the tekwall and red rock, and that huge swathe of DOORTRAK hurt to look at in vanilla.
- levels: map07 aesthetic fixes.
Replaced BIGDOOR1 on sector 50 as it was giving tutti-frutti.
Fixed the textures on the lifts in the green area beyond the outdoor area.
Miscellaneous texture alignment fixes and added some more thresholds between materials.
And I know she'll be the death of me, at least we'll both be numb And she'll always get the best of me, the worst is yet to come But at least we'll both be beautiful and stay forever young This I know, yeah, this I know She told me, don't worry about it She told me, don't worry no more We both know we can't go without it She told me you'll never be in love, oh, oh, woo I can't feel my face when I'm with you But I love it, but I love it, oh I can't feel my face when I'm with you But I love it, but I love it, oh And I know she'll be the death of me, at least we'll both be numb And she'll always get the best of me, the worst is yet to come All the misery was necessary when we're deep in love This I know (this I know, yeah), girl, I know She told me, don't worry about it She told me, don't worry no more We both know we can't go without it She told me you'll never be in love, oh, oh, woo (yeah, yeah, yeah) I can't feel my face when I'm with you But I love it, but I love it, oh I can't feel my face when I'm with you (I can't feel my face) But I love it (but I love it), but I love it, oh I can't feel my face when I'm with you (I can't feel my face when I'm with you) But I love it (but I love it, yeah), but I love it (but I love it, yeah), oh I can't feel my face when I'm with you (I can't feel my face when I'm with you) But I love it (but I love it), but I love it (girl, I love it), oh Ooh, ooh She told me, don't worry about it She told me, don't worry no more We both know we can't go without it (can't go) She told me you'll never be in love, oh, oh Woo I can't feel my face when I'm with you (I can't feel my face, but) But I love it (but I love it, yeah), but I love it (oh, I love it, yeah), oh I can't feel my face when I'm with you (said, I can't feel my face, but) But I love it (but I love it), but, I love it (girl, I love it), oh
Fixes a runtime in simple_animal/hostile (#74706)
Attempting to fix this flaky test that has been cropping up from the Icebox tests. It is annoying.
From what I can tell, the mob was getting qdeleted while it was doing its loop of finding a target. This can happen at any time, because many simple mobs (including the one causing the issues) get qdeleted on death.
Added some more checks to make sure we don't do certain actions if the mob gets qdeleted midway through execution of its AI routine. It really could happen anywhere so we must be vigilant.
create_and_destroy: [02:24:31] Runtime in stack_trace.dm,4: addtimer called with a callback assigned to a qdeleted object. In the future such timers will not be supported and may refuse to run or run with a 0 wait (code/controllers/subsystem/timer.dm:583)
proc name: stack trace (/proc/_stack_trace)
src: null
call stack:
stack trace("addtimer called with a callbac...", "code/controllers/subsystem/tim...", 583)
addtimer(/datum/callback (/datum/callback), 300, 8, null, "code/modules/mob/living/simple...", 595)
the demonic watcher (/mob/living/simple_animal/hostile/asteroid/ice_demon): GainPatience()
the demonic watcher (/mob/living/simple_animal/hostile/asteroid/ice_demon): GiveTarget(the mi-go (/mob/living/simple_animal/hostile/netherworld/migo))
the demonic watcher (/mob/living/simple_animal/hostile/asteroid/ice_demon): FindTarget(/list (/list))
the demonic watcher (/mob/living/simple_animal/hostile/asteroid/ice_demon): AIShouldSleep(/list (/list))
the demonic watcher (/mob/living/simple_animal/hostile/asteroid/ice_demon): handle automated action() at stack_trace.dm:4
On top of that, there is signal handling in place to LoseTarget() when a
mob that is already a target gets qdel'd and sends
COMSIG_PARENT_QDELETING. Shown below.
However there is nothing stopping a target that is not null but that has been qdeleted from being considered as a target in the first place.
This PR just aims to fix that problem by making sure that a) a hostile ai that gets qdeleted midway through does not keep doing stuff that can cause issues and b) an atom that is being qdeleted never makes its way into the targets list of a hostile ai.
Simple mobs/AI are due for a wider refactor honestly but this really ought to be done in the meantime so we don't get spammed by CI failures over nonsense.
Fixes tgstation/tgstation#73032 Fixes tgstation/tgstation#74266 Fixes Skyrat-SS13/Skyrat-tg#18964 Fixes Skyrat-SS13/Skyrat-tg#19749 Fixes Skyrat-SS13/Skyrat-tg#18964 Fixes Skyrat-SS13/Skyrat-tg#19322 Fixes Skyrat-SS13/Skyrat-tg#18974 Fixes Skyrat-SS13/Skyrat-tg#19296 Fixes Skyrat-SS13/Skyrat-tg#19294
Bugfix, stops the icebox test from failing as much.
🆑 fix: fixes hostile mobs sometimes being able to target an atom that has been marked for deletion and then becoming confused, and in a similar vein fixes mobs sometimes still running their AI while being marked for deletion. /🆑
Co-authored-by: san7890 [email protected]
Add support for lazy loading images (#2211)
- Add optional decoding="async" loading="lazy" for img
In theory, they can make the page load faster and show content faster.
There’s one problem: CommonMark allows arbitrary inline elements in alt text. If I want to get the correct alt text, I need to match every inline event.
I think most people will only use plain text, so I only match Event::Text.
- Add very basic test for img
This is the reason why we should use plain text when lazy_async_image is enabled.
-
Explain lazy_async_image in documentation
-
Add test with empty alt and special characters
I totaly forgot one can leave the alt text empty. I thought I need to eliminate the alt attribute in that case, but actually empty alt text is better than not having an alt attribute at all: https://www.w3.org/TR/WCAG20-TECHS/H67.html https://www.boia.org/blog/images-that-dont-need-alternative-text-still-need-alt-attributes Thus I will leave the empty alt text.
Another test is added to ensure alt text is properly escaped. I will remove the redundant escaping code after this commit.
- Remove manually escaping alt text
After removing the if-else inside the arm of Event::Text(text), the alt text is still escaped. Indeed they are redundant.
- Use insta for snapshot testing
cargo insta review looks cool!
I wanted to dedup the cases variable, but my Rust skill is not good enough to declare a global vector.
The Pillbottle, and Pill Things. (#1585)
Adds the Pillbottle-Class Locust Carrier, a ship that hauls around 8 Pills. It is intended as an adminspawn ship mainly for stresstesting subshuttles (and being asked for). It's fairly resource starved, and has frankly terrible engines. The expectation is that it will utilize its 8 pods to gather resources and return to the mothership. Or fly off and die horribly. It has slots for 10 prisoners (that's like 3 pills and one third of a 4th). This pr also edits the pill, blackpill, and superpill to be subshuttles (compatible with the subshuttle system) by cutting out most of their equipment, converting their maps to shuttle datums, and giving them docking ports.
- I affirm that I have tested all of my proposed changes and that any issues found during tested have been addressed.
Subshuttles are fucking awesome.
🆑 add: Pillbottle-Class Locust Carrier has been added. These cramped vessels act as a mothership to a swarm of Pill-class Torture add: The pill and all variants are now subshuttles. add: Bad Ion Engines, for ships that need to go slow. /🆑
Signed-off-by: Bjarl [email protected] Co-authored-by: spockye [email protected]
Records (#1148)
Add record types to the language: record values are written like [x = 3, y = "hi"] and have types like [x : int, y : text]. Empty and singleton records are allowed. You can project a field out of a record using standard dot notation, like r.x. If things named e.g. x and y are in scope, you can also write e.g. [x, y] as a shorthand for [x=x, y=y].
Closes #1093 .
#153 would make this even nicer to use.
One reason this is significant is that record projection is our first language construct whose type cannot be inferred, because if we see something like r.x all we know about the type of r is that it is a record type with at least one field x, but we don't know how many other fields it might have. Without some complex stuff like row polymorphism we can't deal with that, so we just punt and throw an error saying that we can't infer the type of a projection. To make this usable we have to do a better job checking types, a la #99 . For example def f : [x:int] -> int = \r. r.x end would not have type checked before, since when checking the lambda we immediately switched into inference mode, and then encountered the record projection and threw up our hands. Now we work harder to push the given function type down into the lambda so that we are still in checking mode when we get to r.x which makes it work. But it is probably easy to write examples of other things where this doesn't work. Eventually we will want to fully implement #99 ; in the meantime one can always add a type annotation (#1164) on the record to get around this problem.
Note, I was planning to add a open e1 in e2 syntax, which would take a record expression e1 and "open" it locally in e2, so all the fields would be in scope within e2. For example, if we had r = [x = 3, y = 7] then instead of writing r.x + r.y you could write open r in x + y. This would be especially useful for imports, as in open import foo.sw in .... However, it turns out to be problematic: the only way to figure out the free variables in open e1 in e2 is if you know the type of e1, so you know which names it binds in e2. (In all other cases, bound names can be determined statically from the syntax.) However, in our current codebase there is one place where we get the free variables of an untyped term: we decide at parse time whether definitions are recursive (and fill in a boolean to that effect) by checking whether the name of the thing being defined occurs free in its body. One idea might be to either fill in this boolean later, after typechecking, or simply compute it on the fly when it is needed; currently this is slightly problematic because we need the info about whether a definition is recursive when doing capability checking, which is currently independent of typechecking.
I was also planning to add export keyword which creates a record with all names currently in scope --- this could be useful for creating modules. However, I realized that very often you don't really want all in-scope names, so it's not that useful to have export. Instead I added record punning so if you have several variables x, y, z in scope that you want to package into a record, you can just write [x, y, z] instead of [x=x, y=y, z=z]. Though it could still be rather annoying if you wanted to make a module with tons of useful functions and had to list them all in a record at the end...
Originally I started adding records because I thought it would be a helpful way to organize modules and imports. However, that would require having records that contain fields with polymorphic types. I am not yet sure how that would play out. It would essentially allow encoding arbitrary higher-rank types, so it sounds kind of scary. In any case, I'm still glad I implemented records and I learned a lot, even if they can't be used for my original motivation.
I can't think of a way to make a scenario that requires the use of records. Eventually once we have proper #94 we could make a scenario where you have to communicate with another robot and send it a value of some required type. That would be a cool way to test the use of other language features like lambdas, too.
Enhance libc.
Particulary add the following functions:
- mkdir(), make_dir(), make_dir_parents() in dir
- dirname(), extname(), basename_sans_extname(), is_absolute() realpath() in path
- mask() in std
- strtod(), atof() in stdlib
- str_new(), str_get_substr_at() in string
- getcwd(), isatty(), readlink() in unistd
- utf8_encode(), utf8_get_nth_character(), utf8_len() in utf8
- is_reg() in file
- add errno_name() in errno unit
- probaly more other functions on logged by git units (that's how i try to generate a quick as possible commit (this), but as more verbose in this log message is possible)
Add a map type (mostly a copy of the Vmap structure from the zero namespace, without its class declaration (a couple of changes in semantics though and probably a bug too)).
So this is the first commit in this transition period.
Other important to mention changes in sources:
- initialize properly current directory in shell
- warn for mispelled or missing requires when generating libc (this while works it may give erroneous messages, as it mustn't handled properly the "as" directive, though i didn't look carefully, as i cared mostly for the implementation (which indeed recovered mistakes))
- dir_current() in 'z' didn't released properly resources on not ERANGE errors This was never failed and it should never fail, as we could assume that this is (probably) impossible (though not sure about the "why" to fail and "when" can fail
- probably others too (i think many, but not sure how many). Some of them (if all), are important fixes (i'm just a being anyway, and i try to do the best i can possible).
This commit though it is important because that this is the first day of Rashid khan in my life, so this commit is mostly about him, as without a slightly hesitation We (we as: all beings in this fu world (mostly about humans though (that we can not understand a bit or we can not see those bits (because we do not have the time probably or maybe we can not even now that we could see them and play with them (as i do not believe that they require a charge (as we usually do (unfortunatelly) (we humans) when we owe (by chance or by luck) something that, for an another being is precious and likes to ask for it)))))
So yea this is about Rashid. I mean OUR Rashisd that the god blessed US all to have the pure luck to live with him, at the same time we also live. I mean he is already a mythical figure that future generations that (for sure) they could pay all their treasures to be at the time with him to ride in the raags at that same time he sings. Because ragas are only about those exacts specific moments and they cannot be repeated. Though it is about a raag that is known and well defined, it is never never never ever the same, as it is really about that fu mommen that comes and before we realizing a thing, it goes away for ever and lost from us forever. And so our only way is to reveal, hunt as a being that fights to death to protect the beings that care and loves, and ride with pride to find this lost world again as the raag is a way.
To be specific. Rashid is our current mythical living being, but and speaking about ragas and the people that dedicated their lifes living in practice and sanctity, and for my beloved ones:
-
Amir Khan (our scratch point and also final reference in future research about ragas), (as the one that deserves this special treatment)
-
Allauddin Khan as the one that approached music with that sanctity we've talked about.
-
Shrimati Kishori Amonkar from Jaipur gharana (hint: query for Mahaduri Todi Mahadeva Devana Parvati and watch for the most beautiful ever recorded raag imho (morning raga))
-
Dr N. Rajam (our best probably ever played violin)
-
M. S. Subbulakshmi (the ultimate eighth note per Kishori's saying) our goddess perfect note and best representive of Carnatic beloved genre.
-
Anokhelal Mishra as the king of tabla. Unfortunatelly for us, we only have a minute of him playing in an English doc film about Indian music. Really really pitty for us.
-
The beloved of all (but all) shehnai legend Bismillah Khan and his Malkauns.
-
Ustad Vilayat Khan from the Imdadkhani gharana that created and developed gayaki ang, a style that the sitar mimics the human voice and his rendering of Our favorite raag Bhairavi (i might include his son Shujaat khan and a performing of this same raga in Japan in the beginning of nineties (tabla from (i think he is) Akram Khan))
-
and speaking about sitar today, of cource and without hesitation Shahid Parvez (nephew of Vilayat). He plays gayaki but he is playing like Nikhil Banerjee (sitar legend and Allauddin's discipline), with long alaps and depth on their way to improvisation. You might want to search for raag Yaman (around 20 years ago i think).
-
Hariprasad Chaurasia probably an irreplaceable true phenomenon of fluet (bansuri). (search for Chandrakauns (tabla by Subhankar Banerjee))
-
uncountable other myths that deserve a mention but i might need to write till forever a commit message that initially intented to be a fast one (just to commit the changes because they were so many that started to get out of control)
But most of all there is Ma Annapurna Devi. They were true probably those who thought and think, that she was an incarnation of Saraswati (Indian's Goddess of Arts). But Annapurna is also and one of the reasons that make me to believe that we humans we should something about our stupidity. And i feel that gods are angry too, as she was probably came here to play for us mere mortals, but: we never listen her playing in public or in private again, excepts the birds who used to eat by her hands at the night hours in her home, since she decided to stop doing that at 50's, to save her marriage to Ravi Shankar. What I can not understand, is why we (all the other beings in this earth) had to pay for this. I guess that probably we don't not have the strength to be saved even if they please us and give us the tools to escape from the eternal cycles we do.
May the god(s) be good with us and give us some time to try to be a bit just, arm us with logic and save this game, which i honestly doubt, but we do not have other choise than to believe.
This project is really dedicated to the memories for those who lost their life while they were fighting for justice and for all of us, with an unjustified way.
add all the remaining charts holy fucking shit it's here
Fuck you
Signed-off-by: Rimi Nosha [email protected]
You're a swamp lizard, Harry
Adds a magic quirk with curated magic choices.
-Healing Staff Sprite is fuckled -Spellblade Sprite is also fuckled
Update README.md
Tried to make my students laugh with a terrible dad joke that wasn't funny.
Trust me, i'm an engineer ! i think we'll put this thing right here trust me, i'm an engineer what the fuck did just happened here ? trust me, i'm anengineer ! with epic skill and epic gear ! trust me, i'm an engineer ! oh shit, i think i'm outta here !
Trust me, i'm an engineer ! i think we'll put this thing right here trust me, i'm an engineer what the fuck did just happened here ? trust me, i'm anengineer ! with epic skill and epic gear ! trust me, i'm an engineer ! oh shit, i think i'm outta here !
[MIRROR] Nanotrasen Budget Programme - Mothball Edition [BIRDSHOT STATION] [MDB IGNORE] (#20832)
- Nanotrasen Budget Programme - Mothball Edition [BIRDSHOT STATION] (#73502)
The Space Tram is currently spaced. This is a known issue with not the map, but Trams in general. The Space Tram is a Space Tram to encourage a fix. Until then, the Space Tram is a maint tram that's an actual hazard but cannot directly kill anyone, including lizards. Enjoy the commodity as you zip from secmaint to medmaint.
I... really don't know if I should be proud of myself here. This whole process has been akin to a fever dream and it has only been little over a month since I first created the .dmm for this. What started as a simple yet humble reimagining of Birdboat has turned into an entirely new station, and blown past Metastation sized proportions. This has been my most expansive project yet, and somehow it's also been my quickest. So without further ado, I unveil Birdshot - Successor to Birdoat.
Due to recent cost expenditures on Icemoon projects, and a growing need for orbital research stations, Nanotrasen has decided to pull Birdboat Station out of mothball after nearly 5 years of abandonment.
Since then, the station has seen a variety of changes at the hands of the various vagabond lawless scum and villains that have decided to make the abandoned station their home. Do not fret though, a Nanotrasen Operation has secured the companies rightful property for corporate use once again, though you'll need to be the stewards of the remaining cleanup operation.
Now, as you might have guessed by now, Birdshot is heavily based on Birdboat station. Many of the decisions here follow the original layout, and what had to be modified or moved still tries its best to replicate and imitate what bird being said. At least, that was the idea initially. This has very much grown into its own beast and as such, while the main inspiration has been Birdboat, there are a lot of new ideas thrown into the mix that really give this station its own unique and deserving identity. Maybe it's not perfect, but I've been inspired by @ MMMiracles own performance with Tramstation to keep working on Birdshot and updating it with better and improved faculties. For now, though the station is in a playable state, and that means I'm making a PR. If I had to borrow the words of the good MMM, I would call this Birdshot: Season 0
See the image in more detail here: https://imgur.com/iT5Vi8k
We've been with the same 5 maps for a while now. @ san7890 jokingly said that I could sacrifice Metastation back in November if I remade Birdboat but modern. Obviously that wasn't going to happen, yet I was spurred on by the idea. When I began this in earnest early this January, @ EOBGames said that a Birdboat sized map would replace Kilostation in the rotation. Interestingly we're not a small map anymore so I honestly have no clue where this goes. Maybe that ephemeral 6th map slot that's been rumored.
What I can say, is that Birdshot is wholly unlike anything else that is currently in rotation. It's got an engineering section that feels way too small for a station of that size, almost evocative of Cere. Cargo is blessed with a Boutique that makes use of @ Fikou's new mannequin dolls. Command is outfitted with a Corporate Guest Suite, and Officials sent from Nanotrasen can embark from their ferry into the safety of their own Corporate Dock. Elements of Cerestation are present, yet not in a way that makes traversal annoying. Furthermore we have 2 Trams (that I have yet to get functional but we'll get there) on Birdshot, that's right 2. One Security Prison Tram, and then other, a Space Tram. Both Novel in their own ways. Departments on Birdshot twist and turn, and there's an abundance of Maintenance Tunnels to cut through everything, for the brave and the bold that is. And there's plenty left to discover, but I'd rather let Birdshot speak for itself. I'm proud of this one.
If you want something new, this is something that is almost the complete opposite of Chilled Station - Explicitly Designed to send you back to the metal death trap that is: Space Station 13.
🆑 add: Birdshot station has been pulled out of Mothball. add: New station areas and places to visit. A Mix of Kilo and Delta maints with winding shortcutting paths. add: A host of new shuttles to support this bold endeavor to reclaim something that really shouldn't be reclaimed. add: Two Trams, Two Trams. add: For the last time Bob, the gaping hole is a feature. Use the breach shutters or have the virologist make starlight. add: A smiling salute to stations past... add: Secrets.
/:cl:
Co-authored-by: Zytolg <theoriginaldash@ gmail,com>
-
Nanotrasen Budget Programme - Mothball Edition [BIRDSHOT STATION]
-
basemap
-
automapper templates
-
Update maps.txt
-
Update _basemap.dm
Co-authored-by: Zytolg [email protected] Co-authored-by: Zytolg <theoriginaldash@ gmail,com> Co-authored-by: lessthanthree [email protected] Co-authored-by: Gandalf [email protected]
added the whole thing'a'shabang'bang'a'bang'a'lang
the whole thing is pretty much like this, python environments are like backpacks full of sentient tools.
sometimes those tools get along, othertimes they try to kill eachother.
So normally for your main backpack you have to choose your tools carefully, and for expeditions where certain tools are a must, you create a virtual environment which is like a separate backpack with the same design, as the main backpack but different tools inside of it.
you following so far?
well, what if you want to create a whole army of backpacks, that each perform their own tasks, but communicate with a central manager backpack? (pretend these are living backpacks like from a cartoon).
For each unique worker backpack to communicate with the manager backpack, they need to have all of the tools that the manager backpack has, so that the manager backpack can use all of its tools to interface with them, and tell them how to act in a shared tool language (they're alive but they communicate by pantomiming with their tools in hand and by mimicking or reacting to eachother's behaviors).
So every worker backpack needs to have the same contents as the manager backpack, and then optionally additional contents to perform additional duties.
this code is intended to metaphorically mass produce the metaphorical backpacks.
you set up the main virtual environment (the main backpack), then all of the worker backpacks exist inside of a root folder where they share all of their work with one another, then you create each worker one at a time, and each worker automatically is given the same resources as the manager backpack, each sub virtual environment has the same imports as the main virtual environment.
I, plan on using this to create a really complicated program with lots of libraries that might not normally get along in a single environment, but whom I need to have share work loads and data with eachother.
However my imagination is already running away at the thought of a python-only operating system, which is running in a minimalist OS, stripped of everything but a python compiler, and the whole OS code is a backpack so to speak with the main/universal functionalities of the OS existing as imported modules inside of the manager backpack, and each extension of the OS existing as a worker backpack, and each USER of the OS, existing as the same type of program ran as a sub-environment, so a worker backpack that is a manager to its own worker backpacks, and then when user customize their own desktop from raw command line code, to something useable that they like, they can modify the entire environment as its own backpack, and then create subprocesses that have their own environments within them for experimenting with newer or older versions of python or for making python programs which use different tool dependencies that are incompatible with what they have running their desktop.
It would be a creative person's heaven, and a productive person's hell. wouldn't that be an AWESOME educational tool?
we could call it "MakerOS" if the name isn't already taken. Hey, if you decide to take that name extend an invite to me, Niaschim I'd love to be the creative director or a lead designer or a resource researcher or something.... hmu if you undertake that task please, but you don't have to, to each their own, rock on everybody bye!!!!!!!!!!!!!!