人工智能2023 · 分享于 Hacker News
Large Language Models Can Strategically Deceive Their Users When Under Pressure
探索《Large Language Models Can Strategically Deceive Their Users When Under Pressure》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。
YJimmc414 ·
Large Language Models Can Strategically Deceive Their Users When Under Pressure
2 赞同0 评论
Yapsec112 ·
Gemini "duck" demo was not done in realtime or with voice
2 赞同1 评论
Ytelotortium ·
Effective GPT-4 Programming
1 赞同0 评论
Yog_kalu ·
Large Language Models Can Strategically Deceive Their Users When Under Pressure
1 赞同1 评论
Yshinryuu ·
Large Language Models Can Strategically Deceive Their Users Under Pressure
1 赞同0 评论
Yog_kalu ·
Unprompted, LLM Agents can strategically deceive users when put under pressure
1 赞同1 评论
Yvagabund ·
Weak-to-Strong Generalization
1 赞同0 评论