News for hackers. Stuff that matters.
Re:OpenAI's "Own Goal" by sebzim4500 on Thursday March 07, 2024 @06:01AM (#39627527)
If you believe benchmarks then competitors caught up with GPT-4 months ago, but this is certainly not true for my usecases.

In particular, I find GPT-4 hallucines less than Gemini and much less than Claude 3.

Re:OpenAI's "Own Goal" by hackerlight on Thursday March 07, 2024 @06:13AM (#39627602)
Are you using Claude 3 with low temperature and low top p? That's recommended for code generation.