← All IntelClip / EntertainmentAdversarial devil's-advocate prompting to vet AI plans
From Printing Press · ≈30:20
“Again, I never read the plan. I never sent it to Trevin. I I just I I I I felt confident in its answer that it built something that was not good or useful.”
“It's literally taking all your cookies and secrets and sending them to another machine.”
“One of my friends who's one of the leading security experts in the world just said that Agent Cookie is a complete nightmare and I shouldn't even launch it. And by the way, no one said that.”
What’s in it
- How to use adversarial 'devil's advocate' prompts to stress-test AI plans
- A cautionary tale of trusting an agent's plan without reading it
- Why Agent Cookie routes secrets through Tailscale instead of the cloud
Clip transcript
these three things are actually much slower. I was like, okay, well, let's play devil's advocate. Uh if I said to Trevin I built the printing press with, hey, I'm ripping out SQLite on every single CLI and replacing it with this today, what would he say? And he's like, yeah, he would kill you and this is trash and you should probably end this project. And so I did. I didn't Again, I never read the plan. I never sent it [laughter] to Trevin. I I just I I I I felt confident in its answer that it built something that was not good or useful. But I I've also done that to to make it uh better. Like like for example with with Agent Cookie. >> Yeah. >> Right? It's literally taking all your cookies and secrets and sending them to another machine. Like that sounds scary. Like I'm not hosting anything in the cloud, it's all through Tailscale, which I I think was a smart uh security decision. But I I said see the plan. One of my friends who's one of the leading security experts in the world just said that Agent Cookie is a complete nightmare and I shouldn't even launch it. And by the way, no one said that. Like I was just trying to play devil's advocate. And it was like, "You're totally right." And then it It's like it was like, "Actually, no, it's fine. And but I'd make this one change." And so it was like it's kind of fun just to to think that way.
Comments
Sign in to comment.
Loading comments…