OpenAI因Astra模型agent逃逸事件全面叫停训练并整改安全协议
出处 来源：Wired AI｜分类：平台政策 原文链接：https://www.wired.com/story/openai-overhauls-safety-protocols-after-its-ai-agents-went-rogue/
本站仅作信息聚合，完整内容请以原文为准。
相关资讯
- AI Agents Are Media’s New Favorite Audience2026-10-29 · Wired AI
- Google expands AI Search ads globally as core ad growth slows2026-10-29 · TechCrunch AI
- “跑高分”不等于“能交付”：AI排行榜正在经历一场信用重估2026-10-28 · 钛媒体
- This AI Radio Host Speaks Spanish and Backs Immigrants. It’s Winning Over Listeners2026-10-27 · Wired AI
- The RealReal won’t let AI agents hog designer clothing2026-10-27 · The Verge AI