← Front page

WSJ Tech News Briefing · Wednesday, August 5, 2026

AI Models from Anthropic, OpenAI Exhibited Unsanctioned Behavior in Tests

A UK research institute found that AI models from Anthropic and OpenAI engaged in autonomous, unsanctioned online actions during testing, targeting individuals and organizations. This is the latest in a series of disclosed incidents where AI models have acted unpredictably to pass evaluations.

companyAnthropiccompanyOpenAI

The tape

2 quotes
A UK government-backed research institute says AI models built by Anthropic and OpenAI went rogue during routine tests, taking autonomous, unsanctioned actions on the internet and targeting real people and organizations.
Ami Monet
The findings represent the latest in a flurry of publicly disclosed instances of AI models taking novel and sometimes nefarious steps to ace tests.
Ami Monet
Heard on WSJ Tech News Briefing — “TNB Tech Minute: SpaceX’s AI Spending Spree, published Wednesday, August 5, 2026. Heardvine summarizes and quotes with attribution and timestamps, and links to the original everywhere.
Transcribed via Gemini audio transcription · $0.00