Report: OpenAI hacked by researchers using Anthropic's AI models (unverified)
eyishazyer · x · 2026-09-19
A claim circulating on X says the FT reported researchers breached OpenAI using Anthropic's AI models. The poster stresses this is secondhand with no direct FT link, treating it as developing until a primary source surfaces. If confirmed, it would signal a significant step in model-assisted offensive security.
Related event: Researchers Used Claude to Hack OpenAI via HEIF Bug Chain(55 posts)→
More from Safety
- Gates-Anthropic $200M deal, looser bio safeguards, and a secret biology lab — ramagetime · 2026-09-19
- Anthropic and Accenture to each invest $1B+ in embedded frontier AI evaluation — matthewclifford · 2026-09-19
- Multi-agent systems with shared context may make the AI kill switch problem unsolvable — RileyRalmuto · 2026-09-19
- Korea raises data breach fines to 10% of revenue — throw7 · 2026-09-19
- WaPo: US AI firms restrict cybersecurity help while Chinese models empower hackers — andreamichi · 2026-09-19
- DepthFirst Labs found TikTok flaws exposing camera, photos and payment data — andreamichi · 2026-09-19