Update and improve Hungarian translations using Claude 3.5 Sonnet #2549
Conversation
PeterDaveHello
requested review from
Frooodle,
reecebrowne,
Ludy87 and
DarioGii
as code owners
dosubot
bot
added
the
size:XS
|
@Frooodle, if you need help with the review, maybe https://coderabbit.ai/ could be helpful. Reference case: transmission-remote-gui/transgui#1479 (comment) I'm not affiliated with coderabbit, just thought it may help, from my personal experience. |
📃 File Check:
|
|
/deploypr |
🚀 PR Test DeploymentYour PR has been deployed for testing! 🔗 Test URL: http://185.252.234.121:2549 This deployment will be automatically cleaned up when the PR is closed. |
|
@PeterDaveHello can you merge latest changes into your branch |
PeterDaveHello
force-pushed
the
Update-hu_HU
branch
from
8a2fded to
bb5c19c
Compare
|
@Frooodle I rebased on the latest main branch, please take a look. |
|
Sorry was going to merge today but saw some conflicts it wont let me fix it from my side due to your security settings |
|
@PeterDaveHello could you update your branch so we can merge the updates, thanks. |
Leverage Claude 3.5 Sonnet from Anthropic, a frontier LLM model, to enhance translation quality. The previous use of Qwen2.5 7b, a smaller and less advanced AI model, may have affected the quality and user experience(Stirling-Tools#2164). Typically, relying solely on LLMs for translation without verification is not preferred. However, given these concerns, using a frontier LLM model along with references from other language versions should lead to improved results, even for a language I don't even understand. I also use the powerful frontier OpenAI O1 and Google Gemini-1.5-Pro for proofreading, and manually confirmed line breaks to facilitate easier contributions and improvements by others.
PeterDaveHello
force-pushed
the
Update-hu_HU
branch
from
bb5c19c to
3d5b16c
Compare
|
Updated. |
🚀 Translation Verification Summary🔄 Reference Branch:
|
Description
Leverage Claude 3.5 Sonnet from Anthropic, a frontier LLM model, to enhance translation quality. The previous use of Qwen2.5 7b, a smaller and less advanced AI model, may have affected the quality and user experience(#2164). Typically, relying solely on LLMs for translation without verification is not preferred. However, given these concerns, using a frontier LLM model along with references from other language versions should lead to improved results, even for a language I don't even understand.
I also use the powerful frontier OpenAI O1 and Google Gemini-1.5-Pro for proofreading, and manually confirmed line breaks to facilitate easier contributions and improvements by others.
Checklist