• This site is a private, non-commercial website. As such, you're welcome here as long as you were invited. If you would like an invite, reach out to Cliff Spark

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

  • Thread starter Thread starter samrolken
  • Start date Start date
S

samrolken

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?"


Comments URL: Show HN: Why write code if the LLM can just do the thing? (web app experiment) | Hacker News

Points: 63

# Comments: 48

Continue reading...
 
Back
Top