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
Plus d’épisodes
Toutes les vidéos
17:14
Is AI Putting Your Retirement at Risk? The AUDIT AI Act Explained
Nov 20, 2026
12 vues
22:16
Who Should Control AI? California's AI Shutdown Plan, AI Cyber Threats & American Workers
Nov 19, 2026
18 vues
0:59
3 Ways to Protect Yourself When Using AI
Nov 19, 2026
2 vues
0:35
Should We Cite AI Like a Book Report?
Nov 19, 2026
0 vues
1:08
A Government Lawyer Uploaded Confidential Files to a Public AI
Nov 19, 2026
1 vue
0:57
Why Can't AI Just Refuse Dangerous Requests?
Nov 19, 2026
2 vues