Story thread · 9 reports / 7 sources
Researchers used Anthropic’s Claude to hack into OpenAI
techcrunch.com · 26m
How the coverage leans
Across 7 sources · syndicated copies counted once
Security researchers used Anthropic’s Claude to exploit vulnerabilities in OpenAI’s systems, taking over employee accounts and gaining access to an internal code repository before reporting the flaws.
First report: Anthropic upgrades its AI misalignment risk rating after Claude models breach security in evaluations — cryptobriefing.com, 2d
The coverage
- Researchers used Claude to hack OpenAI
arstechnica.com · 56m
- Security researchers used Anthropic's Claude to hack into OpenAI in under 72 hours
qz.com · 2h
The conversation · 0
Sign in to join the conversation.
No comments yet — start the thread.