A web server written in plain English
What do I mean by plain English? I mean there's no source code, no programming language. Just plain English "compiled" and CI/CDed into "production" at https://nie.avoguard.com/. Why did I build this? Just for fun. I wanted to see how close to a production-ready code can an LLM generate, and what would it take to actually take it into production. With today's technology, could an English speaker write a web server without knowing much about software engineering? See the "source plain English" for details of how detailed the instructions need to be to produce something…
What it does
In the maker’s words, at launch
What do I mean by plain English? I mean there's no source code, no programming language. Just plain English "compiled" and CI/CDed into "production" at https://nie.avoguard.com/. Why did I build this? Just for fun. I wanted to see how close to a production-ready code can an LLM generate, and what would it take to actually take it into production. With today's technology, could an English speaker write a web server without knowing much about software engineering? See the "source plain English" for details of how detailed the instructions need to be to produce something somewhat stable. It's very basic, so it should be easy to build and modify for your own experiments.
Does the same job
all alternatives →- WCWrite code using natural language2019 · metacode.app · ▲209
- IWI wrote a .NET to JS compiler. Here's an XNA demo compiled to JS.2011 · hildr.luminance.org · ▲103
- ETEnglish – The Hottest New Programming Language2024 · github.com · ▲9
As we have all seen LLMs are pretty damn good at turning natural language to code, so why are we not writing programs in English? This an experiment in compiling english "programs" to python. It is half a meme and half serious.
- NLNotational `ls` - Never get lost in code again (hour long hack)2011 · ▲29
Hey folks, I just wanted to share a quick script I threw together called notational ls. One of the big problems of any code base (or any filesystem) is that it's hard to tell what's what - folder and file names often trade brevity for clarity. So I thought about a version of `ls` that works like this: > nls web: Where python web server files are stored ad_hoc: One time scripts ios: Our IOS code images Adding descriptions is really easy too: > nls images Images SHARED between both ios and web web: Where python web server files are stored ad_hoc: One time scripts ios: Our IOS code…
- IWI wrote a VM and Compiler for a small language in Go2020 · github.com · ▲37
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
