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…
Why write code if the LLM can just do the thing? (web app experiment) launched on November 1, 2025 with 436 votes, #38 of 9,796 launches that month and more than 99% of that year's launches.
In plain words
This web app experiment tests whether large language models can replace traditional code by handling every HTTP request directly. The app uses an LLM with access to a SQLite database, HTML/JSON response generation, and feedback storage to power a contact manager without pre-written routes or controllers. The system automatically designs database schemas, generates interfaces, and adapts based on user input. While functional—forms submit, data persists, and APIs return results—the approach is impractical at current speeds (30-60 seconds per request) and costs ($0.05 per request), with inconsistent user interfaces. It demonstrates the technical feasibility of AI-driven applications but highlights performance and cost as current barriers.
written from the facts on this page · September 2026
From the sources
Contribute to samrolken/nokode development by creating an account on GitHub.
A web server with no application logic. Just an LLM with three tools. One day we won't need code. LLMs will output video at 120fps, sample inputs in realtime, and just... be our computers. No apps, no code, just intent and execution. But I got curious: with a few hours this weekend and today's level of tech, how far can we get? Everyone's focused on AI that writes code. You know the usual suspects, Claude Code, Cursor, Copilot, all that. But that felt like missing the bigger picture. So I built something to test a different question: what if you skip code generation entirely? A web server with zero application code. No routes, no controllers, no business logic. Just an HTTP server that asks…from github.com
In the maker’s words, at launch
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…
Does a similar job
all alternatives →
Code ModeNov 2025 · github.com · ▲144I’ve been testing a simple idea inspired by Apple/Cloudflare/Anthropic: LLMs are far better at writing a small program than coordinating multiple tool calls. So instead of giving the model 10+ tools, I exposed one: a TypeScript sandbox with access to the same interfaces. The model writes a script → it runs once → done. What changed - +68% reduction in token use - No multi-step drift or retries - Local models (Llama 3.1 8B / Phi-3) became much more reliable Repo: https://github.com/universal-tool-calling-protocol/code-mode Curious whether others have seen…
I wrote an open-source browser alternative for Computer Use for any LLM2024 · github.com · ▲180Hey HN, I made Browser-Use, an open-source tool that lets (all Langchain supported) LLMs execute tasks directly in the browser just with function calling. It allows you to build agents that interact with web elements using natural language prompts. We created a layer that simplifies website interaction for LLMs by extracting xPaths and interactive elements like buttons and input fields (and other fancy things). This enables you to design custom web automation and scraping functions without manual inspection through DevTools. Hasn't this been done a lot of times? Good question, as a general…
Turn any website into a knowledge base for LLMs2024 · embedding.io · ▲305I built this tool because I wanted a way to just take a bunch of URLs or domains, and query their content in RAG applications. It takes away the pain of crawling, extracting content, chunking, vectorizing, and updating periodically. I'm curious to see if it can be useful to others. I meant to launch this six months ago but life got in the way...
Magic Loops – Combine LLMs and code to create simple automations2023 · magicloops.dev · ▲248Howdy! We built this as an experiment in personal-programming, combining the best of LLMs and code to help automate tasks around you. I personally use it to track the tides and get notified when certain conditions are met, something that pure LLMs had trouble dealing with and pure code was often too brittle for. We created it after getting frustrated with the inability of LLMs to deal with numbers and the various hoops we had to jump through to make ChatGPT output repeatable. At the core, Magic Loops are just a series of "blocks" (JSON) that can be triggered with different inputs (email,…
Improve LLM Performance by Maximizing Iterative Development2024 · github.com · ▲104I have been working in AI space for a while now, first at FAANG with ML since 2021, then with LLM in start-ups since early 2023. I think LLM Application development is extremely iterative, more so than any other types of development. This is because to improve an LLM application performance (accuracy, hallucinations, latency, cost), you need to try various combinations of LLM models, prompt templates (e.g., few-shot, chain-of-thought), prompt context with different RAG architecture, different agent architecture, and more. There are thousands of possible combinations and you need a process…
BrowserAI – Run LLMs directly in browser using WebGPU (open source)2025 · github.com · ▲85Check out this impressive project that enables running LLMs entirely in the browser using WebGPU. Key features: - Zero token costs, no cloud infrastructure required - Complete data privacy through local processing - Simple 3-line code integration - Built on MLC and Transformer.js The benchmarks show smaller models can effectively handle many common tasks. Currently the project roadmap includes: - No-code AI pipeline builder - Browser-based RAG for document chat - Analytics/logging - Model fine-tuning interface
More ai this month
the category →
Paintings by AI models: programs run through a simulation of oil paint.
AI · 20d ago · stillwet.art
PixVerse R2▲381A real-time world model you can explore and change
AI · 28d ago · world.pixverse.video
Source: Show HN post ↗ · launch text quoted in part
Launched alongside, November 2025
the whole month →
Guideflow▲1,338Create interactive product demos and step-by-step guides in seconds with Guideflow, the leading AI-powered demo automation tool.
AI · Nov 2025 · guideflow.com
Hardware and software projects by Ali Roberts
Life & fun · Nov 2025 · bitsnpieces.dev
Welltory▲1,028Measure your wellness. Use data to feel great every day.
Work · Nov 2025 · welltory.com
TrustMRR▲833LLM Gateway is a b2b artificial intelligence based in United States, founded in 2025. $259,539/month in verified Stripe revenue. $78,764 MRR. Ahrefs Domain Rating 52/100. growing 55% month-over-month. Track LLM Gateway's verified metrics on TrustMRR.
Growth · Nov 2025 · trustmrr.com
Boing▲782Life & fun · Nov 2025 · boing.greg.technology