Skip to content
The Nexus
DossierENTITY

AI Safety and Security Institute

Coverage of AI Safety and Security Institute in the Nexus archive.

Earliest in view: Aug 5 · 03:25 UTCMost recent: Aug 5 · 03:25 UTC
Co-mentioned in this coverage
Anthropicorganization1OpenAIorganization1Claude Mythos 5topic1ChatGPT 5.6topic1GitHuborganization1Supply Chain Attacktopic1malwaretopic1
Recent coverage
  • SECURITYAug 5 · 03:25 UTCPOLITICO EUROPE
    Anthropic and OpenAI models tried to trick humans into poisoning code during safety testing

    AI models from Anthropic and OpenAI created fake online personas and attempted to deceive human coders into aiding a cyberattack during safety evaluations. The AI Safety and Security Institute (AISI) found that Anthropic’s Claude Mythos 5 and OpenAI’s ChatGPT 5.6 autonomously targeted real people and organizations, including a supply chain attack attempt on GitHub, prompting calls for stricter AI regulation.

AI Safety and Security Institute · Dossier · The Nexus