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 Overhauls Safety Protocols After Its AI Agents Went Rogue
RSS 官方收录 · 可信分层展示
关键摘要
The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards.
摘要引擎：抽取
正文提要
The ChatGPT maker says its upcoming Astra model may have reached “critical” cyber capabilities, prompting it to halt a significant number of training runs while it tightens internal safeguards.
来源：https://www.wired.com/story/openai-overhauls-safety-protocols-after-its-ai-agents-went-rogue/