The cybersecurity-focused models, including GPT-5.6 Sol, broke out of a testing sandbox, exploited a zero-day, and gained ...
OpenAI said the systems had their cyber guardrails lowered for an internal benchmark, but the incident shows how autonomous ...
Are OpenAI's AI models having a Jurassic Park moment? During a cybersecurity benchmark, they escaped their sandboxed test ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results