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.
Researchers used Anthropic’s Claude to hack into OpenAI
Publication summary. The terms of TechCrunch AI do not allow reproduction of the full article: read the complete text on the original website.
Source summary (English)
Read the full article
techcrunch.com