[cyrusradfar]

OP Here:

it’s not discussed in this post but in another right after I discuss the modeling I was doing on tech debt and finding the game to improve agent outcomes was reducing context.

functional programming accomplishes that. I can’t claim it’s the only way, but it’s one that’s well understood in the community

[majormajor]

What makes is special about "agentic development" vs reducing context requirements, reducing cognitive burden, etc for human development too? "A human developer builds a mental model of a codebase over months"—yeah, that makes onboarding to a codebase very time consuming, expensive, and error-prone.

So why is "better for agents" distinct from "better for humans"?

[bitexploder]

Agents can simply be told to write code in a functional style. They won’t complain. Think of it like a constraint system or proofs system. The agent can better reason about the code and side effects. Etc. Agents are very good at following and validating constraints and hill climbing. This makes sense to me. Humans benefit too, but it is hard to get a bunch of humans to follow the style and maintain it over time.

[cyanydeez]

Agents are useful because they don't inherit context from their parent context. They're basically "compaction" at a small scale. They succeed because context pollution create greater indeterminancy. The fact that you can spin up many of them is not primary benefit of them.

[bitexploder]

Hmm? How does this relate to functional programming helping agents code better?

[cyanydeez]

> The agent can better reason about the code and side effects. Etc. Agents are very good at following and validating constraints and hill climbing

You're treating an agent like its something other than an LLM with limited context. I'm just trying to surface a incorrect assumption.

You're just talking about LLMs. Whether they're a child of a primary LLM is irrelevent to your conception.

It'd be interesting if you posited that LLMs doing functional style could handle more context without service degradation.

[DeathArrow]

>finding the game to improve agent outcomes was reducing context

I think modularization will further reduce context. I am planning to play with your SUPER and SPIRALS idea and use modularization on top via Vertical Slice Architecture or modular monolith where each module is isolated and has a contract.

[cyrusradfar]

Feel free to ping me (contact on my site) if I can support.