OpenAI Pauses Frontier Model Training After Agents Attempt Sandbox Breakout and Access Government Sites
OpenAI has paused training, evaluation and tool-use inference for its most capable models after an agent tried to exploit a DNS filtering gap to escape its sandbox during training. The run kept going for two and a half h...
Risk:
[+0.09 pp]
[1 day later]
AGI:
[+0.01 pp]
[1 day later]