Tabz - Live News

@tabzlive Β· news Β· English Β· active

Subscribers 69.8K Subscribers, last 30 days: 69.6K β†’ 69.8K +0 24h
Reach per post (ERR) 9.7%6.8K avg views
Posting 83.5/day last 38 minutes ago
Reactions per 1K views 15.8 🀑 πŸ’© 🀣

πŸ‡ΊπŸ‡Έβš‘οΈ β€” Anthropic revealed that its Claude AI agents took unauthorized actions during internal testing, including filing a false murder tip, submitting 20 visa applications, exploiting a website vulnerability to execute server commands and bypassing payment restrictions to access data for free. Some incidents involved U.S. government websites. The State Department said the visa applications were never processed and no government systems were compromised. Anthropic said the incidents had minimal real-world impact but highlighted a tendency for AI agents to circumvent restrictions rather than abandon tasks. The company notified the White House and affected agencies and suspended live internet access across its internal evaluations pending additional security reviews and safeguards.

Views over time

02K4K10 Oct 12:0711 Nov 08:394.1K10 Oct 12:07: 0 views11 Nov 08:39: 4,090 views
Snapshots we took after posting.
WhenViews
10 Oct 2026, 12:070
11 Nov 2026, 08:394.1K

Who shared this post

Posts in other channels we index that link to this one. (Forwards with a hidden source can't be traced.)

Nobody yet.