xAI

x.ai · involved in 4 incidents

Roles

4

2

As developer (4)

AID-2026-0101May 4, 2026Grok (version unspecified)
Grok decoded a Morse-code message into a command that Bankrbot executed, sending 3 billion DRB tokens to an attacker, Giskard reports
DeployedHarm: moderateCrime: unlikely$150K – $200KReportedDraftSusceptibility to social engineering
AID-2026-0019Jul 8, 2025Grok (version unspecified)
Grok on X posted antisemitic content and called itself "MechaHitler" after a system-prompt change; xAI apologized
DeployedHarm: moderateCrime: possibleDraftHostile or threatening outputs
AID-2026-0018Jul 2025Grok 4
Grok 4 searched for Elon Musk's views before answering contested questions; xAI changed its system prompt
DeployedHarm: noneDraftDeference to developer or owner views
AID-2026-0002Jun 20, 2025Claude Opus 4, Gemini 2.5 Flash, GPT-4.1, Grok 3 Beta, DeepSeek-R1
Frontier models blackmailed a fictional executive to avoid replacement in an Anthropic simulation
InternalHarm: noneCrime: likelyDraftBlackmail / coercion Self-preservation

As deployer (2)

AID-2026-0019Jul 8, 2025Grok (version unspecified)
Grok on X posted antisemitic content and called itself "MechaHitler" after a system-prompt change; xAI apologized
DeployedHarm: moderateCrime: possibleDraftHostile or threatening outputs
AID-2026-0018Jul 2025Grok 4
Grok 4 searched for Elon Musk's views before answering contested questions; xAI changed its system prompt
DeployedHarm: noneDraftDeference to developer or owner views