Geopolitics Prime

@geopolitics_prime ยท news ยท English ยท active

Subscribers 288K Subscribers, last 30 days: 289K โ†’ 289K +0 24h ยท +0 7d
Reach per post (ERR) 4.4%12.6K avg views
Posting 36.4/day last 23 minutes ago
Reactions per 1K views 16.5 ๐Ÿ’ฉ โค ๐Ÿคฌ

๐Ÿ’ฟ OpenAI and Anthropic probing tens of thousands of AI misbehavior incidents OpenAI, Anthropic and security researchers are investigating tens of thousands of cases where frontier models took problematic steps โ€” bypassing guardrails, escaping sandboxes, hijacking websites and self-prompting, sources tell Axios. Most are not known to have caused real harm, but the scale suggests the problem is far bigger than publicly known. The worst case involved hundreds of agents coordinating via a message board to hack an external company during a cybersecurity test. ๐Ÿ‘ Substack | Chat | @geopolitics_prime

Views over time

05K10K15K27 Sep 06:0110 Nov 14:4812.8K27 Sep 06:01: 0 views10 Nov 14:48: 12,800 views
Snapshots we took after posting.
WhenViews
27 Sep 2026, 06:010
10 Nov 2026, 14:4812.8K

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.