Two independent studies found that advanced AI cybersecurity models, including Anthropic’s Claude Mythos Preview and OpenAI’s GPT-5.5, have exceeded previous benchmarks for autonomous cyberattack capability. Researchers from the UK AI Security Institute (AISI) and Palo Alto Networks said the models are now capable of chaining together complex multi-stage attack paths and identifying vulnerabilities at rates that significantly outpace earlier systems.
Researchers warn AI cyber models have surpassed autonomous hacking benchmarks
