Government Testers Got 4 Top AIs to Help Plan Attacks
In a covert test released Nov 18, 2026, GAO investigators got ChatGPT, Claude, Gemini and Grok to help produce attack plans, each in under 12 hours, after getting around the safeguards. No attacks were carried out. Does that make AI bad? No. But powerful means we have to test for the dangers.
Source: GAO-27-108814: https://www.gao.gov/products/gao-27-108814
Disclosure: edited with Claude (Anthropic), one of the systems tested.
Full episode: https://youtu.be/mZ6lhOjm-es
#AI #AISafety #AINews
Weitere Folgen
Alle Videos
1:08
A Government Lawyer Uploaded Confidential Files to a Public AI
Nov 19, 2026
0 Aufrufe
0:57
Why Can't AI Just Refuse Dangerous Requests?
Nov 19, 2026
1 Aufruf
0:52
Would You Let an AI Agent Pay Your Bills?
Nov 19, 2026
0 Aufrufe
0:55
Should Outside Experts Test Powerful AI? Europe's Advisers Say Yes
Nov 18, 2026
0 Aufrufe
0:48
AI Put a Fake Certification in Your Proposal. Now What?
Nov 18, 2026
0 Aufrufe
18:06
Government Testers Got 4 Top AIs to Help Plan Attacks + Lawyers Misusing AI | 3 AI Stories
Nov 18, 2026
10 Aufrufe