Researchers escaped OpenAI's Codex sandbox two ways, one running commands on a developer's machine from its most locked-down mode. OpenAI has patched both.
0 comments
No comments yet.
Related stories
- Hacker News · 55 points · 4 days ago
- Escaping the OpenAI Codex sandbox, twiceaccomplish.aiHacker News · 1 points · 9 days ago
- Researchers used Claude to hack OpenAIarstechnica.comArs Technica · 0 points · 12 days ago
- OpenAI says planned GPT-6.1 is too insecure to releasearstechnica.comArs Technica · 0 points · 1 day ago
- The Verge · 0 points · 1 day ago
- The Verge · 0 points · 8 days ago