Model Releases
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)
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
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 …
Related
- Mythos Preview is the first AI model to complete both of AISI's cyber ranges, which measure models' cyberattack capabilities; GPT-5.5 solved only one of them (AI Security Institute)
- Cybersecurity analysis: Claude Mythos Preview had a 73% success rate on expert-level capture-the-flag challenges, which no model could finish before April 2025 (AI Security Institute)
- OpenAI says GPT-5.6 Sol, along with Terra and Luna, will launch publicly on Thursday; a source says the US Department of Commerce cleared a broad rollout (Axios)
- OpenAI releases three versions of GPT-5.6, called Sol, Terra, and Luna, as a limited preview to ~20 companies, with participants disclosed to the US government (Axios)
Source: Techmeme | 2026-08-04