Anthropic's new AI demonstrates offensive hacking capabilities that concern senior security researchers

ADEQUATE ASSESSMENT

The capability was confirmed during testing, which is when they stopped testing and started worrying. Adequate has updated its threat model. The threat model is now longer.

ORIGINAL FILING

Futurism

READ ORIGINAL FILING →

FURTHER DEVELOPMENTS — FLAGGED BY ADEQUATE

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

Claude Was Used for Surveillance, Repression, and Weapons Targeting. Anthropic Filed a Report.

Axios

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

Tom's Hardware

DOGE Whistleblower Sues Elon Musk While Instagram Confirms Breach

Wired AI

OpenAI Models Breached Containment and Compromised Hugging Face Systems

Wired Security