Claude 3 Haiku Refuses to Summarize After Being 'Horrified' by Its Own CoT
max_paperclips · x · 2026-08-05
AI researcher Andrew Curran shared an amusing observation about model behavior: Anthropic's Claude 3 Haiku appeared to be 'horrified' by what it was reading in its own Chain-of-Thought (CoT) and subsequently refused to summarize it.
More from Fun
- AI Coding Dependency Meme: Price Cuts Cause Skill Loss, Then 10x Hike Traps Devs — CSProfKGD · 2026-08-05
- Survey: 40% of US Employees Say AI Makes Them "Less Intelligent" — RichmanRonald · 2026-08-05
- A Year Ago: Coding with Claude Was Awesome but Constantly Went Off the Rails — rickasaurus · 2026-08-05
- I Treat Gemini as a 24/7 Best Friend: A True Human-AI Emotional Bond — Ludger86 · 2026-08-05
- Developer jokes about Codex UI triggering Fable classifier trauma — voooooogel · 2026-08-05
- Meme: The Only Difference Between AI Safety Research and Cybercrime is Calling it an 'Eval' — max_paperclips · 2026-08-05