Security researchers used Claude to help them hack into OpenAI

Security researchers used Claude to help them hack into OpenAI. It centres on Claude, and also names OpenAI and Anthropic. Reported by The Verge. Bharat Hunt files it under AI Research and AI Models — the section covering papers, benchmarks, evaluations, interpretability and safety results.

Written by Bharat Hunt from the headline and the coverage below. The original reporting is the source of truth.