AI & machine learning2022 · shared on Hacker News
Language Models (Mostly) Know What They Know
Explore Language Models (Mostly) Know What They Know, 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.
Comment #46210857 Comment #42002816 Comment #41995964 Comment #41504226 Comment #41418486 Comment #40573657 Comment #39500821 Comment #38323750 Comment #38295741 Comment #38256005 Comment #38243115 Comment #38194773 Comment #38186850 Comment #37947603 Comment #37874556 Comment #37864677 Comment #37863911 Comment #37825430 Comment #37824605 Comment #37794805 Comment #37673886 Comment #35800908 Comment #32372492 Comment #32327011
Ylouthy ·
Hallucination is inevitable: An innate limitation of large language models
308 points474 comments
Ysurprisetalk ·
SimpleQA
229 points84 comments
Ypanabee ·
AlphaFold won’t revolutionise drug discovery
203 points103 comments
Ybenocodes ·
LLMs know more than they show: On the intrinsic representation of hallucinations
137 points140 comments
Yyarapavan ·
GPTs and Hallucination
134 points205 comments
YXcelerate ·
Transformers know more than they can tell: Learning the Collatz sequence
129 points45 comments
Yctoth ·
Chinchilla's Wild Implications
88 points32 comments
YPaulHoule ·
Language Models (Mostly) Know What They Know
43 points6 comments
YDuximo ·
AI is growing faster than companies can secure it, warn industry leaders
31 points51 comments
Yjasondavies ·
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
28 points9 comments
Yanarbadalov ·
"Hallucinating" AIs Sound Creative, but Let's Not Celebrate Being Wrong
27 points15 comments
YJohnHammersley ·
ChatGPT and other AI tools could disrupt scientific publishing
8 points2 comments
Yjdmark ·
Rats have an imagination, new research suggests
6 points1 comments
Yofermend ·
LLM Hallucinations: why they occur and how to avoid them
5 points1 comments
Ymagoghm ·
I disagree with Geoff Hinton regarding "glorified autocomplete"
4 points0 comments
Ysebg ·
The Geometry of Truth: Do LLM's Know True and False
3 points0 comments
Yog_kalu ·
The Internal State of a Large Language Model Knows When Its Lying
2 points1 comments
Ynyrikki ·
LLMs can't self-correct in reasoning tasks, DeepMind study finds
2 points1 comments
Ylogicallee ·
Ask HN: What is your standard for judging when AGI exists?
2 points0 comments
Yjyli7 ·
How Will AI Learn Next?
1 points1 comments
Yog_kalu ·
The Geometry of Truth: Emergent Linear Structure in How LLMs Represent Truth
1 points1 comments
Ym_kos ·
Role play with large language models – Nature
1 points1 comments
YAnon84 ·
Language models and linguistic theories beyond words
1 points0 comments