Comment by baq
8 days ago
true - but the way LLMs are trained, google's RLVR is different from anthropic's is different from openai's. you'll get very good results sending the same 'review this change' prompt (literally) to different models.
8 days ago
true - but the way LLMs are trained, google's RLVR is different from anthropic's is different from openai's. you'll get very good results sending the same 'review this change' prompt (literally) to different models.
No comments yet
Contribute on Hacker News ↗