logoalt Hacker News

threethirtytwo • today at 3:52 PM • 0 replies • view on HN

Maybe this is where prompt engineering comes into play. Force the model out of the statistically simple solution by making it self aware of what it’s doing.

Reinforcement training on tasks that are successful and not just valid answers can help with this in the sense that we give models tasks and reward the ones that complete the task most correctly rather then some human qualitative rating on the answer.