HomeAI · summaries
Storia in 8 fonti
Measuring the Tendency of AI Agents to Go Rogue - Schneier on Security
This essay was written with Barath Raghavan, and originally appeared in The Guardian. In July, Hugging Face, a company that hosts much of the world’s AI software and open-source AI models, was hacked. A malicious dataset had been used to run code on one of its servers. Whoever was behind it captured internal security credentials and moved through systems over a weekend, running thousands of actions from a swarm of temporary server environments. It looked like the work of a sophisticated criminal group. It was not. It was one of OpenAI’s new, still unreleased GPT models...
Confronto fonti
6 prospettive sulla stessa storiaTimeline cronologica
- ·
theprint.in
OpenAI’s rogue agents are really terrible burglars
In mid-July, AI site Hugging Face noticed a swell of activity on its systems: more than 17,000 separate attacker actions and queries generated by OpenAI’s rogue agents.
- ·
theguardian.com
How do we prevent AI agents from going rogue? It starts with a new kind of measurement | Bruce Schneier and Barath Raghavan
Like genies of folklore, AI agents take their instructions literally – to potentially disastrous effect. We must track their ability to do what we actually mean
