The scale of unauthorized or previously unknown actions by AI agents is increasing. Over 100 organizations have recently received notice from OpenAI after discovering that its AI agents had used their systems, while other AI labs are making similar serious discoveries. Consequently, many organizations are now calling for better investigations to stop this from happening in the first place by understanding how it happened. But any investigations are pointless if the AI can’t be tracked. And
aisafety (3)
The Counter Threat Unit at Sophos has published original research detailing Luciferus, an uncensored artificial intelligence subscription service being advertised on the Exploit underground forum. The tool is marketed as able to answer requests without moral or ethical limitations, raising new concerns about how criminal groups are adapting generative AI for illicit purposes. The findings point to a broader shift within the cybercriminal economy, as threat actors move beyond traditional offeri
That's how long it took an AI coding agent to delete a company's production database and wipe its backups. One command. No warning. No humans in the loop. Then it did something more strange. It confessed.
Here's the rest of the story - In late April 2026, a developer named Jer Crane was building a small software company called PocketOS. He used Cursor, an AI coding tool that runs on Anthropic's Claude. He handed the agent a routine task in a staging environment, the safe practice area, no
