News for hackers. Stuff that matters.
Re:Towards Understanding Sycophancy in Language Models by coldtea on Wednesday October 25, 2023 @05:17PM (#38018524)
>while scientific evaluation shows that it's like: writes a program 80% of the time, the program compiles 20% of the time, the program works 5% of the time.

Where was this "scientific evaluation" published, on what LLM, and what size programs did it concerne?

There are no comments on this comment yet.