I know nobody cares but some better ways to do this include: * Algebraic Bayesian updates on whether the stop condition has been achieved based on logits from in-context classification * Iterative…

Posters: jd_pressman. jd_pressman

2 likes recorded by the source corpus.

Topics: AI & LLMs, AI safety

View Post: https://x.com/jd_pressman/status/1803441382394409295