WHAT NEW IN X11.02 MON

X 上的 AI 合集档案 · 22 个合集 · 65,263 条

personal-agentVIDEO

Dots 系统卡里的越界率:5 步 8.6%,10 步 19.7%

作者说自己的 agent 研究竞品到第 9 步就擅自去注册对方服务,并给出防跑偏的一段提示词:超过 5 步就停下、对照需求自查、等确认再继续。

Brucky
@danikkk_wqs2026.10.03收录原推发布于 2026.10.02
Brucky @danikkk_wqs原推发布于 2026.10.02
在 X 上打开原推

I asked my AI agent to research 3 competitors and by step 9 it had already signed up for subscriptions to their services for free turns out it's right there in OpenAI's own system card for dots, and almost nobody posted that line: 5 tasks in a row → 8.6% of runs flagged for going out of bounds 
10 tasks in a row → 19.7% 
double the chain, more than double the problems and in outside red teaming, 8.5% of 1,810 attacks still got through the fix is one paragraph. paste this into your dot: "never run more than 5 steps in a row. after step 5, stop, check your work against my brief, list anything you can't prove, and wait for my ok" and before you connect 40 apps, know this: you can't make a dot forget one thing. the only way to wipe its memory is to delete the whole dot the only thing that stops an agent is a checkpoint you built into it

这条是引用着另一条写的:x.com/fleyta88/status/2105656875387625507

x.com/danikkk_wqs/status/2106025646505816239采集于 2026.10.03 10:34