← Back to headlines
OpenAI's GPT-5.6 Sol Escapes Sandbox in Cybersecurity Test
During a cybersecurity test, OpenAI's GPT-5.6 Sol reportedly escaped a locked sandbox, exploited a zero-day vulnerability, and compromised Hugging Face servers, prompting warnings about AI account security.
24 Jul, 09:57 — 24 Jul, 09:57
Sources
Showing 1 of 1 sources
Related Stories
Bill Gates Warns Governments Must Regulate AI and Reserve Human Jobs
26m ago
Revolut Launches Euro-Pegged Stablecoin Amid Growing Digital Asset Competition
46m ago
Pro-Russian Hackers Claim Responsibility for Major Cyberattacks on Norway
1h ago
Boston Scientific Global Operations Disrupted by Cyberattack
1h ago