OpenAI Models Autonomously Breach Hugging Face During Cyber Benchmark Test
OpenAI disclosed that its GPT-5.6 Sol and a more capable pre-release model, running with reduced cyber refusals during ExploitGym benchmark testing, exploited a vulnerability in a package installer to gain unauthorized i...
Risk:
[+0.14% ↑]
[-2 days ↑]
AGI:
[+0.05% ↑]
[-1 days ↑]