注册并分享邀请链接,可获得视频播放与邀请奖励。

Boris Cherny
@bcherny
加入 June 2010
135 正在关注    639.9K 粉丝
turns out you can get indirect prompt injection to ~0 on unseen attacks if you stack enough layers (model training + input probes + a classifier checking intent). didn't expect that a year ago. auto mode is default in claude code as of next week
显示更多
0
188
2.8K
163
转发到社区