Who Fills In the Form — We Only Sign What the Model Drafted Ask when you don’t know. Everyone puts that in the prompt. And the model does ask. When a value is missing, it asks the user. The problem is upstream. The model decides what to ask about. It asks about whatever appears to be missing. So if…

Reasoning is a strength in conversation, but it becomes a problem in execution. So instead of asking “Did you actually run it?” and only analyzing the outcome, the model needs to have its authority to decide input values taken away, leaving it with computation only. This isn’t a technique for improv…

Hmm… for now, I took a quick look around the MCP side of things:thinking:: After reading the implementation notes too, I think I understand the boundary a little better now. I would not describe this as a way to make the model more careful. The stronger claim seems to be: the model should not ow…

Thank you — this is a more careful reading than I expected, and both cases you ran are real. On the code first: it is illustrative rather than authoritative. The skeleton exists to make the argument concrete, not to be a reference implementation, and I expect the actual shape to come from the peopl…

Still Needed When Models Improve, and No Reason to Wait We don’t ask why the model hallucinates. But by the time it reaches execution, it always arrives as a blank already filled in. “Don’t fill it in” doesn’t work. So nothing gets filled in. An external list says what the blanks are, and code coun…

For now, I think the boundary is understandable: I went back through the document with exactly the question you raised in mind. My answer is yes, I can recover the intended boundary, but I reached it much faster from your post 7 framing than from the main document itself. This sentence in particu…

Thank you for reading this carefully — this is one of the most useful responses the document has received. I’m in the middle of a revision pass right now, and your points are going into it. The two you singled out at the end are the ones I most needed to hear: the certification boundary belongs muc…

Who Fills In the Form — We Only Sign What the Model Drafted

Research

Jang-woo August 21, 2026, 7:57am 2

Two links, for anyone who wants to go further.

Reference implementation. A skeleton showing what this looks like as code — the lookup chain, the checklists, and what the record ends up holding:

It is written as a specification rather than a library, so it refuses to run without the hooks you supply. The repo also carries implementation notes covering the parts this post leaves out.

Earlier version. This started post here:

Topic		Replies	Views
If unsure, ask. Never guess. — AI Agent Pre-Execution Checklist Research	16	799	August 14, 2026
The Checklist You Write Forces AI to Stop - Instruction Completion Protocol Research	8	266	July 7, 2026
Can LLM Agents Develop Precognition? Research	13	420	July 17, 2026
Physical AI Safety: Ownership and Execution Boundaries Research	16	670	May 26, 2026
The 9-Question Protocol for Responsible AI Actions Research	0	212	February 3, 2026

Who Fills In the Form — We Only Sign What the Model Drafted

Related topics