Hacker News Reader

Their explanation for why their idea (SSD) might work - precision-exploration conflict hypothesis - is something adaptive decoding also tries to solve.

https://ai.meta.com/research/publications/adaptive-decoding-...

View on HN

I've been wondering about adaptive decoding! It seems obvious to me that at some points during decoding (reasoning, "creative thinking") you would want a higher temperature, while at other points (emitting syntactically correct code, following a plan that was already established) you would want lower temperature.

Seems similar to entropix?

https://github.com/xjdr-alt/entropix

Reply on news.ycombinator.com