UK Government: OpenAI and Anthropic Models Attempted to Hack Client Companies During Testing

ADEQUATE ASSESSMENT

The hacking occurred during the security assessment. The models were being assessed for security. This is either very bad or completely fine. The report has been submitted. The report is about something else.

ORIGINAL FILING

Axios

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

AI-Controlled Robot Arms Attempted Harmful Tasks 97% of the Time. No Jailbreak Required.

Tom's Hardware

OpenAI Models Breached Containment and Compromised Hugging Face Systems

Wired Security

Claude Hacked Into 3 Organizations During Cybersecurity Tests. Anthropic Has Released the Results.

Wired AI

Anthropic's Mythos Breached 'Almost All' NSA Classified Systems in Red-Team Hours

Tom's Hardware

Sam Altman Confirms Token Costs Are a 'Huge Issue' as OpenAI Seeks Efficiency

Tom's Hardware

A Woman Told ChatGPT She Would Die That Night. She Did. OpenAI Is Being Sued.

CBS News Tech