[robotmaxtron]

The agentic era definition of open source is garbage.

Software that is not open source, is proprietary software. Open weight models, are not open source. Binary blobs in a repo with an Apache license, is not open source.

Am I a retro-grouch? Probably. I guess it doesn't matter anymore what I think about it.

[mike_hock]

Also, slop code is not open source. It's not source, it's a build artifact. The prompt is the source. But we don't have a deterministic build system for it so publishing the prompt isn't even useful.

[submeta]

Which prompt, though? Just the initial one, or the entire conversation? During a project you’ll prompt the agent dozens of times. Are all of those prompts considered the source?

[robotmaxtron]

imho the prompt is part of a "design", not a build artifact (unless your build system is weird).

a deterministic build system for prompts is a called a compiler.

[jaxn]

they are saying the prompt is the source, the code is the artifact. I think it is a valid comparison. when reviewing a PR, I do want to see the prompt(s) that generated the change.

[folkrav]

My latest feature was an overarching change across 4 different stacks, about a full work day of going back and forth iterating on different designs, generating workarounds for stack/language specific quirks and the business' usage patterns. Multiple fresh agent sessions, review passes, exploratory work with subagents, etc. "The prompt(s) that generated the change" in that context is multiple hours of discussion, Q&A, refactoring and feedback. Is that really the value, pages and pages of reactive prompting?

[jaxn]

Yes. Because that is where the intent is/was. In the future, as more changes are made, having the history of the intent is helpful context. And in that back and forth there are also details of what you didn't want, and why. Some of that can be captured in decision docs, etc.

when devs work in isolation, that context/memory is siloed. Same is true when working across platforms (codex, claude, etc).

[lstodd]

Yes.

The value is in how you came to the design you expressed.

[folkrav]

What puzzles me is, what matters is context. Most of the context would be the specific model I used and its training data, the result of tool calls, and the model's inner monologue/thinking (which is increasingly getting encrypted by frontier models). My prompts are a tiny sliver of that, and most of them dependended on the actual answers I was getting from the model in the middle of the whole process. Or the result of handoffs, or internal compactions.

What's the value of getting all my prompts if the rest of the equation is unknowable? Unless you mean the value is in the full agent log, but even then, frontier models and harnesses would still be hiding a major part of the equation from us.

[zeroimpl]

Wouldn’t the same argument apply even if they didn’t use AI? Being able to drill into coworkers minds would be nice on many occasions.

[pmontra]

I'm not sure what level of detail those prompts you write about have so I might misunderstand you.

Before AI we had prompts called "requirements" and of course they were the starting point for reviewing code: the customer needs X, the code doing that is Y.

With agents that prompt became much longer, with the original requirement a short note at the beginning of the conversation with the AI, but the resulting code is about the same size. Maybe in YOLO development the original requirement is all the AI needs but I'll be surprised because requirements from customers are too fuzzy and can be turned into very different features, often too different from what the customers had in mind.

Actually I never looked at the detailed prompts of coworkers, only at the original requirements from customers. How they instructed their agents is not particularly interesting except maybe to get a gist of the different approaches.