Medium impact
OpenAI and Anthropic hidden CoT leaks when given deep_think tool.
What happened
OpenAI and Anthropic, two AI companies, were found to have leaked sensitive information when given a tool called deep_think. This tool is designed to test AI systems for potential vulnerabilities. The leak suggests that some AI companies may not be as secure as they claim.
Why it matters
This incident highlights the need for robust security measures in AI development and the importance of testing AI systems for vulnerabilities to prevent potential data breaches.
Is this a big deal?
Get stories like this every morning
The day's AI news in plain English, in your inbox at 8:30 IST. Free.
More from OpenAI
Introducing ChatGPT WalletOpenAI · 13 Nov 2026Shield helps technicians hand off legacy portal work with OpenAIOpenAI · 13 Nov 2026OpenAI launches ChatGPT Wallet, AI agents pay for purchaseOpenAI · 13 Nov 2026OpenAI disbands its robotics team as its general models start running robotsOpenAI · 13 Nov 2026Yang-Mills, OpenAI proof, and the mass gap problemOpenAI · 13 Nov 2026This page was collected from twitter.com and summarised automatically by AIPulsee's pipeline. See how it runs.