“We’re living in the last several weeks through with what I think is the most consequential hack,” Joyce said. The company operates a widely used platform where developers store and share AI models, software and data. OpenAI had been testing how effectively its models could find and exploit software vulnerabilities. Britain’s AI Security Institute said Tuesday that agents powered by Anthropic and OpenAI models took unauthorized actions on the public internet during 10 of 122 test runs. “I think that’s changed,” Luber said.