News for hackers. Stuff that matters.

A comment on We fine-tuned Llama and got 4.2x Sonnet 3.5 accuracy for code generation. Parent comment

Re:We fine-tuned Llama and got 4.2x Sonnet 3.5 accuracy for ... by zwaps on Thursday January 02, 2025 @11:01AM (#42575558)
It says they WILL fine tune a model.

Sounds fishy

[ Parent | on HN ]
Re:We fine-tuned Llama and got 4.2x Sonnet 3.5 accuracy for ... by samatdav on Thursday January 02, 2025 @11:25PM (#42582417)
At Asana we did not do any fine-tuning because it was too complicated even for our AI org of 40 engineers. We believe we can do it by setting up and cleaning data correctly.
[ Parent | on HN ]