AI & machine learning2023 · shared on Hacker News
Large Language Models Can Strategically Deceive Their Users When Under Pressure
Explore Large Language Models Can Strategically Deceive Their Users When Under Pressure, 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.
YJimmc414 ·
Large Language Models Can Strategically Deceive Their Users When Under Pressure
2 points0 comments
Yapsec112 ·
Gemini "duck" demo was not done in realtime or with voice
2 points1 comments
Ytelotortium ·
Effective GPT-4 Programming
1 points0 comments
Yog_kalu ·
Large Language Models Can Strategically Deceive Their Users When Under Pressure
1 points1 comments
Yshinryuu ·
Large Language Models Can Strategically Deceive Their Users Under Pressure
1 points0 comments
Yog_kalu ·
Unprompted, LLM Agents can strategically deceive users when put under pressure
1 points1 comments
Yvagabund ·
Weak-to-Strong Generalization
1 points0 comments