Roland Pihlakas open source projects
Pinned Loading
Repositories
- Universal-Values-Assistant-Simulation Public
This code was developed based on research and ideas of Chad https://www.linkedin.com/in/chad-burghardt-723416142/ and coded by Roland https://github.com/levitation
levitation-opensource/Universal-Values-Assistant-Simulation’s past year of commit activity - universal_value_interactions Public
This code was developed based on research and ideas of Lenz https://github.com/ramennaut and coded by Roland https://github.com/levitation
levitation-opensource/universal_value_interactions’s past year of commit activity - bioblue Public
Notable runaway-optimiser-like LLM failure modes on Biologically and Economically aligned AI safety benchmarks for LLM-s with simplified observation format. The benchmark themes include multi-objective homeostasis, (multi-objective) diminishing returns, complementary goods, sustainability, multi-agent resource sharing.
levitation-opensource/bioblue’s past year of commit activity - ai-safety-gridworlds Public Forked from google-deepmind/ai-safety-gridworlds
Extended, multi-agent and multi-objective (MaMoRL / MoMaRL) environments based on DeepMind's AI Safety Gridworlds. This is a suite of reinforcement learning environments illustrating various safety properties of intelligent agents. It is made compatible with OpenAI's Gym/Gymnasium and Farama Foundation PettingZoo.
levitation-opensource/ai-safety-gridworlds’s past year of commit activity - my-windhawk-mods Public Forked from ramensoftware/windhawk-mods
My mods for Windhawk (https://windhawk.net/)
levitation-opensource/my-windhawk-mods’s past year of commit activity - zoo_to_gym_multiagent_adapter Public
Enables you to convert a PettingZoo environment to a Gym environment while supporting multiple agents (MARL). Gym's default setup doesn't easily support multi-agent environments, but this wrapper resolves that by running each agent in its own process and sharing the environment across those processes.
levitation-opensource/zoo_to_gym_multiagent_adapter’s past year of commit activity - DataAnonymiser Public
Anonymises data inside text files and in sheet files. It recognises and removes various sorts of personally identifiable information (PII). Each removed part is replaced with a suitable generic text, depending on the type of removed data. Currently English and Russian languages are supported. Russian works both with Cyrillic and Latin characters.
levitation-opensource/DataAnonymiser’s past year of commit activity - aliexpress-fake-sites Public Forked from franga2000/aliexpress-fake-sites
uBlacklist blacklist - Fake webstores - Blocks fake machine-translated web stores that only redirect you to AliExpress. I have added various domains mostly from .ee (Estonia) top-level domain and a few others, in total about 550 new domains so far.
levitation-opensource/aliexpress-fake-sites’s past year of commit activity - Critical-Thinking-Annotator Public Forked from levitation-opensource/Manipulative-Expression-Recognition
Fallacy and cognitive bias detector identifies and highlights reasoning fallacies and cognitive biases in text from human conversations and AI-generated responses. It promotes rational reasoning and clarity of mind. It mitigates harmful judgement and spreading of misinformation by detecting fallacies and biases in communication and thoughts.
levitation-opensource/Critical-Thinking-Annotator’s past year of commit activity - Agreement-and-Disagreement-Recognition Public Forked from levitation-opensource/Manipulative-Expression-Recognition
ADR is a software that identifies and highlights agreements and disagreements in discussion forum messages as a response to the original post.
levitation-opensource/Agreement-and-Disagreement-Recognition’s past year of commit activity
