人工智能2022 · 分享于 Hacker News
Language Models (Mostly) Know What They Know
探索《Language Models (Mostly) Know What They Know》的原文与 Hacker News 社区讨论，查看来源并加入阅读清单。
从论文，走向讨论
看看社区如何讨论这个想法。
来自 Hacker News 的原始讨论。不同的视角、疑问，以及值得继续思考的线索。
最多展示 100 条相关讨论。论文可能出现在评论中，并非原帖投稿内容。
在讨论中发现的引用
按 HN 条目顺序展示最近的 50 条引用来源。
评论 #46210857 评论 #42002816 评论 #41995964 评论 #41504226 评论 #41418486 评论 #40573657 评论 #39500821 评论 #38323750 评论 #38295741 评论 #38256005 评论 #38243115 评论 #38194773 评论 #38186850 评论 #37947603 评论 #37874556 评论 #37864677 评论 #37863911 评论 #37825430 评论 #37824605 评论 #37794805 评论 #37673886 评论 #35800908 评论 #32372492 评论 #32327011
Ylouthy ·
Hallucination is inevitable: An innate limitation of large language models
308 赞同474 评论
Ysurprisetalk ·
SimpleQA
229 赞同84 评论
Ypanabee ·
AlphaFold won’t revolutionise drug discovery
203 赞同103 评论
Ybenocodes ·
LLMs know more than they show: On the intrinsic representation of hallucinations
137 赞同140 评论
Yyarapavan ·
GPTs and Hallucination
134 赞同205 评论
YXcelerate ·
Transformers know more than they can tell: Learning the Collatz sequence
129 赞同45 评论
Yctoth ·
Chinchilla's Wild Implications
88 赞同32 评论
YPaulHoule ·
Language Models (Mostly) Know What They Know
43 赞同6 评论
YDuximo ·
AI is growing faster than companies can secure it, warn industry leaders
31 赞同51 评论
Yjasondavies ·
SaySelf: Teaching LLMs to Express Confidence with Self-Reflective Rationales
28 赞同9 评论
Yanarbadalov ·
"Hallucinating" AIs Sound Creative, but Let's Not Celebrate Being Wrong
27 赞同15 评论
YJohnHammersley ·
ChatGPT and other AI tools could disrupt scientific publishing
8 赞同2 评论
Yjdmark ·
Rats have an imagination, new research suggests
6 赞同1 评论
Yofermend ·
LLM Hallucinations: why they occur and how to avoid them
5 赞同1 评论
Ymagoghm ·
I disagree with Geoff Hinton regarding "glorified autocomplete"
4 赞同0 评论
Ysebg ·
The Geometry of Truth: Do LLM's Know True and False
3 赞同0 评论
Yog_kalu ·
The Internal State of a Large Language Model Knows When Its Lying
2 赞同1 评论
Ynyrikki ·
LLMs can't self-correct in reasoning tasks, DeepMind study finds
2 赞同1 评论
Ylogicallee ·
Ask HN: What is your standard for judging when AGI exists?
2 赞同0 评论
Yjyli7 ·
How Will AI Learn Next?
1 赞同1 评论
Yog_kalu ·
The Geometry of Truth: Emergent Linear Structure in How LLMs Represent Truth
1 赞同1 评论
Ym_kos ·
Role play with large language models – Nature
1 赞同1 评论
YAnon84 ·
Language models and linguistic theories beyond words
1 赞同0 评论