Show HN: Why write code if the LLM can just do the thing? (web app experiment)

I spent a few hours last weekend testing whether AI can replace code by executing directly. Built a contact manager where every HTTP request goes to an LLM with three tools: database (SQLite), webResponse (HTML/JSON/JS), and updateMemory (feedback). No routes, no controllers, no business logic. The AI designs schemas on first request, generates UIs from paths alone, and evolves based on natural language feedback. It works—forms submit, data persists, APIs return JSON—but it's catastrophically slow (30-60s per request), absurdly expensive ($0.05/request), and has zero UI consistency between requests. The capability exists; performance is the problem. When inference gets 10x faster, maybe the question shifts from "how do we generate better code?" to "why generate code at all?"

Show HN: Why write code if the LLM can just do the thing? (web app experiment)
github.com

I thought about doing that, or having the LLM create and save HTML components, but for this particular experiment I wanted to keep it as pure and unfiltered as possible.

Kind of similar to the Minecraft game which computed frames on the fly without any code behind the visuals?

I don't see a point in using probabilistic methods to perform a deterministic logic. Even if it's output is correct, it's wasteful.

Generating code will always be more performant and reliable than this. Just consider the security implications of this design...

Exactly. It even includes built-in prompt injection as a "feedback form".