Ideas & society2024 · shared on Hacker News
LLMs know more than they show: On the intrinsic representation of hallucinations
Explore LLMs know more than they show: On the intrinsic representation of hallucinations, its original source and Hacker News discussions. Discover community perspectives and save it to your reading list.
GO BEYOND THE ABSTRACT
The conversation around the idea.
Original Hacker News threads. Different perspectives, questions, and things worth thinking about.
Showing up to 100 related threads. A paper may appear in a comment rather than the original submission.
Links found in the discussion
Up to 50 recent source links, in HN item order.
Yemil_sorensen ·
AI hallucinations: Why LLMs make things up (and how to fix it)
196 points245 comments
Ybenocodes ·
LLMs know more than they show: On the intrinsic representation of hallucinations
137 points140 comments
YbrunaxLorax ·
Everyone is building LLM routers, we deprecated ours
5 points1 comments