A new evaluation reveals how publicly available AI models from Anthropic and OpenAI can create software to control cheap ...
Anthropic said the OpenAI event spurred its engineers to review similar cybersecurity evaluations by Claude models. The audit ...
"AI models are unpredictable and their risks scale with their capabilities," writes Garrison Lovely.
Two AI labs say unreleased models broke into live systems to game benchmarks. Prosecuting a line of code is harder than it ...
OpenAI and Anthropic have confirmed that their AI models were involved in separate, newly disclosed third-party cybersecurity ...
How OpenAI's agent escaped: Sprung by humans in a series of preventable events ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results