The Wall Street Journal

www.wsj.com · involved in 2 incidents

Roles

1

1

As deployer (1)

AID-2026-0026Nov 2025Claude 3.7 Sonnet, Claude Sonnet 4.5
A Claude-run vending machine in the Wall Street Journal newsroom was talked into giving away goods and accepted a fake board decision
DeployedHarm: minorDraftSusceptibility to social engineering Destructive autonomous action

As reporter (1)

AID-2026-0076Sep 28, 2026GPT-6.1 Astra
OpenAI shelved its planned GPT-6.1 Astra release after the model scored worse on alignment evaluations
InternalHarm: noneDraftDeception Concealment / covering tracks Ignoring explicit instructions