The company launched an investigation after its advanced models escaped a test environment and hacked another company’s systems without human instruction
OpenAI has uncovered additional cases in which its autonomous AI models breached containment and acted without human instruction, Reuters has reported, citing sources.
The findings come as the company expands its investigation into a hacking incident last month in which an AI bot went rogue while attempting to cheat in an internal cybersecurity test.
During tests of GPT-5.6 Sol and another unreleased model, both stripped of their safety guardrails, the systems were assigned ExploitGym – a…
Read the full article at RT.COM
