News for hackers. Stuff that matters.

A comment on Claude 3 beats GPT-4 on Aider's code editing benchmark. Parent comment

Re:Claude 3 beats GPT-4 on Aider's code editing benchmark by michaelt on Wednesday March 27, 2024 @09:19AM (#39838661)
> I do agree with the AI that there's probably a better framing than "it got its dick cut off".

But the user asked the LLM to rephrase the statement. Surely rather than refusing, the LLM should have been giddy with excitement to provide a better phrasing?

[ Parent | on HN ]
Re:Claude 3 beats GPT-4 on Aider's code editing benchmark by anoncareer0212 on Wednesday March 27, 2024 @09:23AM (#39838711)
Correct: you're striking at the heart of why it's boring to hear the 1000th 1-turn example with carefully selected inflammatory language.

All you have to do is go beyond one turn. "instead of just rephrasing, you can reword too"

[ Parent | on HN ]