Re:Notes on OpenAI's new o1 chain-of-thought models
by bartread on Friday September 13, 2024 @08:24AM
(#41530538)
I don't know that "confabulation" is right either: it has a couple of other meanings beyond "a fabricated memory believed to be true" and, of course, the other issue is that LLMd don't believe anything. They'll backtrack on even correct information if challenged.
[ Parent
| on HN ]
There are no comments on this comment yet.