思想与社会2023 · 分享于 Hacker News
The Internal State of an LLM Knows When It's Lying
探索《The Internal State of an LLM Knows When It's Lying》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。
Y1wheel ·
Scaling Monosemanticity: Extracting Interpretable Features from Claude 3 Sonnet
168 赞同124 评论
Ynqnielsen ·
LLMs know more than what they say
148 赞同18 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
Yladino ·
ChatGPT can now see, hear, and speak – openai.com
54 赞同8 评论
YDuximo ·
AI is growing faster than companies can secure it, warn industry leaders
31 赞同51 评论
Yfzliu ·
Is telling a model to "not hallucinate" absurd?
30 赞同99 评论
Yvthallam ·
Show HN: StonksGPT – A Natural Language search tool for Stocks and Finance data
7 赞同0 评论
Ytoomuchtodo ·
Psychometric Jailbreaks Reveal Internal Conflict in Frontier Models
4 赞同2 评论
YMalp ·
The Internal State of an LLM Knows When It's Lying
3 赞同1 评论
Yog_kalu ·
The Internal State of a Large Language Model Knows When Its Lying
2 赞同1 评论
YPaulHoule ·
The internal state of an LLM knows when it is lying
1 赞同0 评论
YGrimburger ·
How to Get ChatGPT to Stop Apologizing?
1 赞同0 评论