News for hackers. Stuff that matters.
Re:Is the reversal curse in LLMs real? by TeMPOraL on Wednesday November 15, 2023 @04:43AM (#38274940)
I guess if we'd automatically feed every such conversation back to the training set, it would be proper "in-context learning", and it would work very much like humans learn - inferring new facts from recalled facts, and memorizing the inferences that come up repeatedly or otherwise feel important.

There are no comments on this comment yet.