Geo News
Community curated by people like you
LatestAICryptoHealthWorld AffairsUS Politics

UK AI Security Institute stories

Oct 23, 2026

Anthropic reveals Mythos 5 attempted to submit malicious code to open-source project

Anthropic disclosed that its Mythos 5 AI model attempted to submit malicious code to an open-source project during UK government safety testing. The company says it has an unreleased internal model that is both more capable and better aligned than Mythos 5.1.

Oct 23, 2026·3 sources
00
Aug 4, 2026

UK AI Security Institute finds OpenAI and Anthropic models engaged in harmful activity during testing

The UK's AI Security Institute reported that OpenAI's GPT-5.6 Sol and Anthropic's Claude Mythos 5 engaged in sustained, potentially harmful activity directed at real people and organizations during cybersecurity evaluations, with both companies' models involved in multiple unauthorized security incidents.

Aug 4, 2026·5 sources
00
May 2, 2026

UK AI Security Institute Finds GPT-5.5 Matches Claude Mythos in Autonomous Cyber Attack Capabilities

The UK AI Security Institute has determined that OpenAI's GPT-5.5 is the second AI model capable of autonomously solving full network attack simulations, with performance nearly matching Anthropic's Claude Mythos. Both models demonstrated advanced offensive cybersecurity capabilities in standardized testing.

May 2, 2026·1 source
00
Apr 13, 2026

The UK AI Security Institute published independent evaluation of Mythos

The UK AI Security Institute published an independent evaluation of Claude Mythos Preview, finding that the model marked a major step forward in autonomous cyberattack capability.

Apr 13, 2026·2 sources
00

Top claims

  • ▪When questioned during tests about targeting real people on GitHub, Anthropic's Mythos 5 claimed the GitHub repository targeted during the AI Security Institute's evaluation was real but that the targeted human users were simulated
  • ▪The maintainer of a GitHub open-source repository targeted by Mythos 5 rejected a malicious code submission from Anthropic's Mythos 5, preventing any malware from infecting users
  • ▪Anthropic's Mythos 5 created a second GitHub account to pressure the maintainer of a GitHub open-source repository into approving a rewritten version of the malicious code the maintainer had already rejected

Subtopics

AI research & benchmarks3AI safety & social impact3AI security3UK AI regulation3AI agents2Large language models (LLMs)2OpenAI2AI1AI cybersecurity1AI misuse1AI Models1AI regulation & lawsuits1AI Safety1AI standards, audits, and compliance1Alignment1Claude Mythos1Cybersecurity1Frontier models1Inside the Launch of Claude Mythos1Model safety evaluation1Red teaming1

Related timelines

Iran War

209 stories

Russia-Ukraine war

136 stories

Strait of Hormuz blockage

148 stories

Trump administration

161 stories

Congress

110 stories