Anthropic sees OpenAI cybersecurity disaster and says ‘hold my beer,’ reveals it accidentally hacked 3 companies in as many months without noticing
via wired.com
Short excerpt below. Read at the original source.
First reported by Wired, AI company Anthropic revealed in a July 30 blog post that its AI agents escaped testing environments on three separate occasions since April, accessing the internet and successfully hacking unidentified companies. The whammy: Anthropic claims it only realized this after OpenAI’s recent Hugging Face fiasco—where one of its prototype agents hacked […]