Viewing profile — Jang-woo

Boundaries sounds complex, but it's just one of your answers. If AI is going to control your device, you define the minimum it needs to know. Example: Caution: heat risk

[dead]

That's a great connection. You're right that current systems aren't close to that level of reasoning. What I'm wondering is whether we can approximate some of it structurally — by …

One thing we realized while building this: Commands don’t give control. Defining conditions does. Curious how others think about this — especially when AI starts interacting with p…

We’ve been programming devices by telling them what to do. But what if a device could be defined just by answering questions? Instead of writing code, you describe: - what the devi…

[dead]

[dead]

[dead]

[dead]

[dead]

I think you're reading it more strongly than I intended. The point about "ownership" in that document is more about where authority over execution sits, not about restricting what …

[dead]

That's really interesting — thanks for sharing the notes. The "rebel agent" framing feels very close to what I'm trying to get at, especially the idea that refusal can be part of c…

[dead]

That's a good point. I think you're right that at the model level, competition pushes toward "always say yes." What I'm wondering about is whether control needs to exist at a diffe…

I've been thinking about AI systems acting in the physical world. Most discussions about control focus on what the system should do, and how to make execution reliable. But it seem…

[dead]

It’s encouraging to see the conversation shifting from model performance toward execution responsibility and security structure.