Hacker News
- Reasoning models don't always say what they think https://www.anthropic.com/research/reasoning-models-dont-say-think 267 comments
Linking pages
- New research shows your AI chatbot might be lying to you - convincingly | TechSpot https://www.techspot.com/news/107429-ai-reasoning-model-you-use-might-lying-about.html 243 comments
- Researchers concerned to find AI models hiding their true “reasoning” processes - Ars Technica https://arstechnica.com/ai/2025/04/researchers-concerned-to-find-ai-models-hiding-their-true-reasoning-processes/ 91 comments
- Hallucinations in LLMs: A Side Effect of Being Trained to Be Right? - Coriana's Blog https://coriana.github.io/2025/04/14/llm-hallucinations.html 1 comment
Related searches:
Search whole site: site:anthropic.com
Search title: Reasoning models don't always say what they think
See how to search.