News for hackers. Stuff that matters.
Re:Is the reversal curse in LLMs real? by thomastjeffery on Wednesday November 15, 2023 @10:40AM (#38277861)
LLMs don't derive or follow rules. LLMs don't have anything to do with rules.

They implicitly recognize (and model) patterns in text, then continue those patterns.

While the patterns that an LLM has modeled may align to the high abstraction we call language, LLMs actually work at a much lower level of abstraction: plain text.

It's the content of that text that is significant. We encode language into text, and LLMs infer something "close enough" to language by blindly modeling it.

Re:Is the reversal curse in LLMs real? by mistermann on Thursday November 16, 2023 @09:31AM (#38289950)
You don't actually know what LLM's are "doing", comprehensively. You are describing your map/intuition of what is going on - it is a cultural convention (and a well enforced one at that), so an easy mistake to make.