Hacker News new | ask | show | jobs
by koakuma-chan 148 days ago
Is there evidence that LLMs adhere to this format better than to JSON? I doubt that.
2 comments
iLoveOncall 148 days ago
It is 100% guaranteed that they DON'T. Toon is 3 months old, it's not used by anyone, and it's therefore not in the training set of any model.
link
TheTaytay 148 days ago
Their benchmarks compare it against other formats as input, not as output.
link
koakuma-chan 148 days ago
Now it makes sense.
link