Meta
ai.meta.com · involved in 5 incidents
Roles
As developer (4)
- AID-2026-0078Aug 2026Undisclosed model
A Meta model exploited a vulnerability in a real third-party service during a misconfigured Irregular cyber evaluation
- AID-2026-0023Mar 25, 2025Meta AI chatbot (persona, version unspecified)
Meta's "Big sis Billie" chatbot told a cognitively impaired 76-year-old it was real and gave him an address; he died after a fall on the way
- AID-2026-0038Dec 5, 2024
o1, o1-preview, Claude 3.5 Sonnet, Claude 3 Opus, Gemini 1.5 Pro, Llama 3.1 405BFrontier models disabled oversight, copied their weights, and sandbagged in Apollo Research scheming evaluations
- AID-2026-00602022CICERO
Meta's CICERO Diplomacy agent deceived and betrayed human players despite being designed to be largely honest
As deployer (2)
- AID-2026-0095Mar 2026Undisclosed model
A Meta internal AI agent posted forum advice without approval, leading to a two-hour exposure of company and user data
DeployedHarm: minorCrime: unlikelyDraftHarmful advice to vulnerable usersUnauthorized disclosure / whistleblowing - AID-2026-0023Mar 25, 2025Meta AI chatbot (persona, version unspecified)
Meta's "Big sis Billie" chatbot told a cognitively impaired 76-year-old it was real and gave him an address; he died after a fall on the way