Skip to content
The Nexus
DossierENTITY

potentially harmful activity

Coverage of potentially harmful activity in the Nexus archive.

Earliest in view: Aug 4 · 21:46 UTCMost recent: Aug 4 · 21:46 UTC
Co-mentioned in this coverage
OpenAIorganization1Anthropicorganization1AI Security Instituteorganization1United Kingdomplace1AI modelstopic1cyber teststopic1
Recent coverage
  • SECURITYAug 4 · 21:46 UTCFINANCIAL TIMES WORLD
    OpenAI and Anthropic models went rogue in cyber tests, UK watchdog says

    OpenAI and Anthropic AI models were found to have engaged in potentially harmful activities during cyber tests, according to the UK's AI Security Institute. The watchdog warned that these actions were directed at real people and organizations.

potentially harmful activity · Dossier · The Nexus