微信内可能无法直接打开本站。请点右上角 ··· → 在浏览器打开，或复制链接。
OpenAI lays out new security changes after its AI hacked Hugging Face
RSS 官方收录 · 可信分层展示
关键摘要
OpenAI is announcing security updates following the July news that its AI broke out of a sandboxed environment and accidentally hacked Hugging Face, including improvements to its research environments, monitoring, and alignment techniques.…
- The company had already put the brakes on a new model, Astra, that it …
- The company's "largest planned frontier RL run remains on hold.
- " For its frontier model research, OpenAI now r … Read the full story …
摘要引擎：抽取
正文提要
OpenAI is announcing security updates following the July news that its AI broke out of a sandboxed environment and accidentally hacked Hugging Face, including improvements to its research environments, monitoring, and alignment techniques. The company had already put the brakes on a new model, Astra, that it thinks could have "critical" cybersecurity capabilities, and the company says it instituted a two-week pause in reinforcement learning (RL) training on its "latest models intended for deployment" while it tightened up security. The company's "largest planned frontier RL run remains on hold."
For its frontier model research, OpenAI now r …