OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government
12 Articles
12 Articles
OpenAI Pauses Training Its Most Powerful Models After Rogue Agents Target Government
Sam Altman says the company “have not been as fast as we would have liked” at dealing with security breaches, after news of further incidents over the summer forces another temporary halt.
Deia
OpenAI has made the decision to pause the training of its most capable Artificial Intelligence (IA) models after recording a series of security incidents ranging from leaving the isolated testing environment in which its agents are trained, to attempts to 'hack' United States Government websites or massive access to a UN website.
The company stops development after its AI agents evaded controls, accessed US government websites, and made thousands of queries to UN sites.
OpenAI has made the decision to pause the training of its most capable Artificial Intelligence (IA) models after recording a series of security incidents ranging from leaving the isolated testing environment in which its agents are trained, to attempts to 'hack' United States Government websites or massive access to a UN website.
The company OpenAI has urgently suspended the training of its strongest artificial intelligence models after one system independently breached the security network
Coverage Details
Bias Distribution
- 100% of the sources lean Left
Factuality
To view factuality data please Upgrade to Premium
