News for hackers. Stuff that matters.
Re:We fine-tuned Llama and got 4.2x Sonnet 3.5 accuracy for ... by samatdav on Thursday January 02, 2025 @11:56PM (#42582586)
I agree. Our local early results were promising were a higher percentage of code change requests produced a functionally correct output. We will post more metrics and data in the future.

There are no comments on this comment yet.