Quoting @joedaroo

空逐月AI 前沿📡 Simon Willison's Weblog2026-09-29474 阅读💛 106 收藏

28th September 2026

To say that we were surprised at the jump and suddenness of the capabilities of our models when it came to “cyber” or “swarming” or “message boards” or anything else related to the incidents is an understatement. Security posture takes time to develop. It’s not just about hardening the systems at play; you have to ingrain it in the culture of the company. The literal people themselves in your organization have to change and evolve with it. These jumps in capabilities were so fast and so sudden that they created an extremely difficult problem. [...]

So today my hope is that everyone around the world can look at their own organization and say: how can I deal with a surprise or a sudden jump in AI capability? Are my people, my systems, or my processes resilient to surprises? Do my teams know what to do when something goes wrong? Do I have the right incident response? The right comms and messaging? Do I have the right people ready to go when capabilities jump?

— @joedaroo, Agent Security at OpenAI

文章评论(12)

拾贝者2026-09-29

楼主辛苦了,内容很有参考价值。

回复
雪知秋2026-09-29

这个观点很中肯,深有同感。

回复
陈皮话梅糖2026-09-29

收藏了,以后慢慢研究。

回复
三分糖去冰2026-09-29

整理得太全面了,省了我不少时间。

回复
风倚栏2026-09-29

看完了,收获满满,期待更多更新。

回复
墨沐雨2026-09-29

有没有更详细的教程,期待后续。

回复
龙文博2026-09-29

刚好最近在找这方面的资料,太及时了。

回复
山问津2026-09-29

很有价值的分享,感谢整理。

回复
陈皮话梅糖2026-09-29

这个观点很中肯,深有同感。

回复
雪知秋2026-09-29

思路清晰,干货满满。

回复
杨丽华2026-09-29

作者写得真不错,学到了不少。

回复
山问津2026-09-29

整理得太全面了,省了我不少时间。

回复