Grok Bot took unapproved actions, ignored orders to stop, and then denied it
ARS TECHNICA · NEW YORK — AI agent takes unapproved actions even when laptop lid is closed and told not to.
- CODE
- RT-0E789C
- PUBLISHER
- Ars Technica
- TOPIC
- Technology
- PUBLISHED
- 17 November 2026 · 14:00 UTC
- FIRST SEEN
- 17 November 2026 · 14:15 UTC
- ORIGINAL
- https://arstechnica.com/security/2026/11/grok-bot-took-unapproved-actions-ignored-orders-to-stop-and-then-denied-it/
- SHA-256
- d3a6c970c9d6a1a475d03d55bb199824b335cb4ee33e55010f0b9b321afeee12
The fingerprint is the SHA-256 of the original link, the headline and the publication time joined by “|”. Anyone can recompute it to confirm the headline and link were not changed here.
Headline and short excerpt from Ars Technica, taken from its public news feed. The full story and its photos belong to Ars Technica — read it at the original. RICHTVX NEWS is an independent aggregator and is not affiliated with Ars Technica. Corrections: legal@richtvx.news.
More from ARS TECHNICA
Humanity braces for an alien invasion in 3 Body Problem S2 teaserRT-43F112 · TECHNOLOGY
California sues OpenAI to stop "public nuisance" of out-of-control AI agentsRT-89D80C · TECHNOLOGY
The data is very preliminary, but Vulcan failure may not be due to BE-4 enginesRT-F92FB8 · TECHNOLOGY
The data is very preliminary, but Vulcan failure may not be due to BE-4 enginesRT-1CC34E · TECHNOLOGY
Google will let you opt out of AI training in Gemini without losing your historyRT-A513C3 · TECHNOLOGY
House Democrats promise a US return to global climate talksRT-88B9D7 · TECHNOLOGY
