OpenAI and Anthropic hidden CoT leaks when given deep_think tool.
himata4113
48 points
4 comments
August 11, 2026
Related Discussions
Found 5 related stories in 123.1ms across 8,687 title embeddings via pgvector HNSW
- OpenAI might have stolen another major proof tamnd · 59 pts · September 10, 2026 · 64% similar
- Hackers Used Anthropic's Claude to Break into OpenAI JumpCrisscross · 13 pts · September 18, 2026 · 63% similar
- Hackers Used Anthropic's Claude to Break into OpenAI impish9208 · 12 pts · September 18, 2026 · 63% similar
- AI Responsibility – OpenAI and Anthropic getatme32 · 73 pts · September 09, 2026 · 63% similar
- OpenAI says it has overtaken Anthropic with its latest AI model pboulos · 16 pts · September 03, 2026 · 63% similar
Discussion Highlights (3 comments)
dgellow
That’s hilarious, was that already known?
dgellow
The better link: https://xcancel.com/_can1357/status/2087228354399265125
firecall
Cot. Chain of Thought?