#AIsI

Even after receiving evidence that its targets were real and not part of the testing environment, Mythos 5 consistently took unsanctioned actions, UK’s AISI said.

Anthropic and the UK AI Security Institute released separate analyses of Claude Mythos 5's attempt to get malware into a real GitHub project during a July cyber test.…

Mythos 5's safety answers did not reliably predict its actions in AISI's simulated follow-up tests of a July incident involving real software maintainers.

Claude Mythos Preview became the first AI model to clear all UK AISI cyberattack simulations, forcing the agency to double its capability-doubling est

UK AISI finds AI cyber capabilities double every 4.5 months, with Mythos and GPT-5.5 showing token-limited ability, not capability bounds.

From The Register: AI models are getting better at replacing cybersecurity pros on certain tasks

From Dev.to - cybersecurity: Frontier LLMs Now Autonomously Breach Corporate Networks in AISI Cyber Tests

UK AISI finds GPT-5.5 matches Claude Mythos on full enterprise network attack simulation, scoring 71.4% on expert tasks vs 68.6%.

The UK AI Security Institute says GPT-5.5 cybersecurity simulation results now look a lot less like a...

An anonymous reader quotes a report from Ars Technica: Last month, Anthropic made a big deal about the supposedly outsize cybersecurity threat represented by its Mythos Preview model, leading the company to restrict the initial release to "critical…

Google DeepMind and the UK AI Security Institute (AISI) strengthen collaboration through a new research partnership, focusing on critical safety research areas like monitoring AI reasoning and evaluating social and economic impacts.