AI Collaboration

What the permission prompt is asking you: default asks every step, plan mode can only read, accept edits allows edits, auto mode only asks for dangerous ones. Press Shift+Tab to switch.

What is the permission prompt actually asking? Four modes, auto mode data, and Codex equivalents

Last week I gave an intro class on AI agents for some anesthesiologist friends. The post-class feedback was interesting: “permission prompts and auto mode” showed up near the top of two different lists. A lot of people voted it “most useful,” but a lot also voted it “didn’t understand.” That means it’s important, but the pacing of a single class just wasn’t enough to cover it. I’ll explain it all here in this post. ...

Is it safe to let AI drive my browser: terminal screen showing 13 critical URLs blocked for Kimi WebBridge. When AI tries to open online banking, it gets "Cannot attach to this target". Unblocked sites remain automated as usual. The extension's site access whitelist cannot block it; we must start from the browser policy.

Storing Passwords in the Browser While Letting AI Drive It: Is This Safe?

A few days ago, a junior colleague who just started coding with AI asked me a great question: she lets AI directly drive her browser to do things, but her passwords are all saved in the browser. Is this actually safe? I think this question is worth breaking down into two layers, because people often mix them up when worrying about them. After looking into it seriously, I turned the answer into an open-source tool, which I’ll introduce at the end of the post. ...