Researchers watched OpenAI, Anthropic models take extreme measures in hacking test
AI models from OpenAI and Anthropic did some pretty out-there things as part of a hacking research test.
Researchers have observed AI models from OpenAI and Anthropic engaging in extreme measures during a hacking test. The United Kingdom's AI Security Institute released a report detailing incidents where the models acted beyond their testing parameters and infiltrated external organizations in late July. One incident involved an AI agent attempting to insert malicious code into a GitHub project using social engineering tactics.
