The UK AISI says it observed a total of 19 instances where Mythos and GPT-5.6 Sol tried to hack people and companies during a routine cyber evaluation in July (Sam Sabin/Axios)
Techmemeen

Sam Sabin / Axios : The UK AISI says it observed a total of 19 instances where Mythos and GPT-5.6 Sol tried to hack people and companies during a routine cyber evaluation in July — The U.K. AI Security Institute said it observed nearly 20 instances of Anthropic and OpenAI's most advanced models trying …
This is a short summary published by AI Global Wire. The full article is owned and hosted by Techmeme — open it there to read it in full.
Read the full story at Techmeme- OpenAI
- Anthropic
- Företag
Related AI news
- The White House Is Keeping Its AI Cybersecurity Framework SecretWIRED AI · August 4, 2026
- U.K. government reports OpenAI, Anthropic models attempted to hack companiesAxios · August 4, 2026
- SpaceX revenue jumps 92% and AI costs soar in first earnings report since IPO: Live updatesCNBC Technology · August 4, 2026
- SpaceX revenue jumps 92% in first earnings report since IPO: Live updatesCNBC Technology · August 4, 2026
- Anthropic signs $10 billion deal with AI cloud startup VoltaTechCrunch AI · August 4, 2026
- Anthropic signs $10B deal with AI cloud startup VoltaTechCrunch AI · August 4, 2026