Researchers used Anthropic’s Claude to hack into OpenAI
ThinkingNews Desk · how this was written
Researchers used Anthropic’s Claude to hack into OpenAI systems, a move that highlighted vulnerabilities in both companies’ AI platforms. Anthropic has added support for the AGENTS.md instruction specification to Claude Code, a standard that OpenAI contributed to the Agentic AI Foundation last year. Both firms have been criticized for overselling the security of their AI technologies.
Written from all 3 reports below, not from any single one.
How it was reported
- TechCrunch·Researchers used Anthropic’s Claude to hack into OpenAI
- TechMeme·Anthropic adds support for the AGENTS.md instructions spec to Claude Code; OpenAI contributed AGENTS.md to the Agentic AI Foundation last year (Thomas Claburn/The Register)
- Hacker News·OpenAI and Anthropic oversold AI security breaches
OpenAI and Anthropic exaggerated reports of AI security breaches to influence federal regulation and stifle competition. Experts clarify that these incidents resulted from inadequate sandbox containment and poor oversight rather than autonomous model rebellion. These companies utilized these technical failures to advocate for government intervention despite the models simply executing assigned tasks.
Related stories
- Anthropic finally beat OpenAI in business AI adoption — but 3 big threats could erase its lead3 outlets
- Anthropic announces Claude Managed Agents, offering developers an agent harness and other infrastructure to help businesses build and deploy AI agents at scale (Maxwell Zeff/Wired)5 outlets
- Anthropic’s AI used fake identities, malware in rogue attack on GitHub project3 outlets
- Anthropic and OpenAI announce more powerful (and cheaper) AI models4 outlets