Story
OpenAI and Anthropic hidden CoT leaks when given deep_think tool.
1 report
1 website
1 discussion
Latest report
Overview
guys you do know you can just disable thinking, and instead give it a "deep_think" tool, and it will call it with internal CoT reasoning format right? gl fixing that We can finally talk about it: We found a way to extract hidden reasoning of frontier models using a vulnerability in the APIs of every frontier AI company. We verified that our reasoning token count matches billed API thinking tokens ...
Summary from twitter.com.
Reports
One report so far. Additional coverage will appear here when it is linked to this story.
Community reactions
Each reaction summarizes sampled comments from the linked discussion.
Hacker News · twitter.com
Hacker News discussion ↗
Historical count: 4 · 4 saved in sample · Historical sample
Awaiting analysis