Compile English specs into 22 MB neural functions that run locally
We built ProgramAsWeights (PAW) — https://programasweights.com You describe a function in English — like "classify if this message is urgent" — and PAW compiles it into a tiny neural program (22 MB) that runs locally like a normal Python function. No API keys, no internet after compilation, deterministic output. It's for tasks that are easy to describe but hard to code with rules: urgency triage, JSON repair, log filtering, tool routing for agents. pip install programasweights import programasweights as paw f = paw.compile_and_load("Classify if this is urgent or not.") f("Need your…
In plain words
ProgramAsWeights (PAW) compiles English descriptions of functions into 22 MB neural programs that run locally as Python functions without requiring API keys or internet access. Users describe a task in plain language—such as classifying message urgency, repairing JSON, or filtering logs—and PAW generates a deterministic executable. Designed for developers building agents or automation systems, it handles classification and routing tasks that are difficult to express as traditional rules.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
We built ProgramAsWeights (PAW) — https://programasweights.com You describe a function in English — like "classify if this message is urgent" — and PAW compiles it into a tiny neural program (22 MB) that runs locally like a normal Python function. No API keys, no internet after compilation, deterministic output. It's for tasks that are easy to describe but hard to code with rules: urgency triage, JSON repair, log filtering, tool routing for agents. pip install programasweights import programasweights as paw f = paw.compile_and_load("Classify if this is urgent or not.") f("Need your signature by EOD") # "urgent" Compilation takes a few seconds on our server. After that, everything runs on your machine. Each program is a LoRA adapter + text instructions that adapt a fixed pretrained interpreter (Qwen3 0.6B). The model itself is unchanged — all task behavior comes from the compiled program. On our evaluation, this 0.6B interpreter with PAW reaches 73% accuracy. Prompting the same 0.6B directly gets 10%. Even prompting Qwen3 32B only gets 69%. Also runs in the browser (GPT-2 124M, WebAssembly): https://programasweights.com/browser You can also use it in your AI agents by copying the prompt here: https://programasweights.com/agents Source: https://github.com/programasweights Try it out: https://programasweights.com
Does the same job
all alternatives →- LALocalGPT – A local-first AI assistant in Rust with persistent memoryFeb 2026 · github.com · ▲331
I built LocalGPT over 4 nights as a Rust reimagining of the OpenClaw assistant pattern (markdown-based persistent memory, autonomous heartbeat tasks, skills system). It compiles to a single ~27MB binary — no Node.js, Docker, or Python required. Key features: - Persistent memory via markdown files (MEMORY, HEARTBEAT, SOUL markdown files) — compatible with OpenClaw's format - Full-text search (SQLite FTS5) + semantic search (local embeddings, no API key needed) - Autonomous heartbeat runner that checks tasks on a configurable interval - CLI + web interface + desktop GUI - Multi-provider:…
- HTHow to write a tiny compiler2017 · blog.klipse.tech · ▲224
- RRRunprompt – run .prompt files from the command lineNov 2025 · github.com · ▲134
I built a single-file Python script that lets you run LLM prompts from the command line with templating, structured outputs, and the ability to chain prompts together. When I discovered Google's Dotprompt format (frontmatter + Handlebars templates), I realized it was perfect for something I'd been wanting: treating prompts as first-class programs you can pipe together Unix-style. Google uses Dotprompt in Firebase Genkit and I wanted something simpler - just run a .prompt file directly on the command line. Here's what it looks like: --- model: anthropic/claude-sonnet-4-20250514 output:…
- SBSpaCy – Build tomorrow's language technology products with Python2015 · spacy.io · ▲93
- PLPython library for functional programming2017 · github.com · ▲129
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
Launched alongside, April 2026
the whole month →
- AG
Thought the resources for GPU arch were lacking, so here we are
Life & fun · Apr 2026 · jaso1024.com
- IB
Built a ~9M param LLM from scratch to understand how they actually work. Vanilla transformer, 60K synthetic conversations, ~130 lines of PyTorch. Trains in 5 min on a free Colab T4. The fish thinks the meaning of life is food. Fork it and swap the personality for your own character.
AI · Apr 2026 · github.com
- BC
Life & fun · Apr 2026 · sam-burns.com
- IB
With social media and now AI, its important to keep the indie web alive. There are many people who write frequently. Blogosphere tries to highlight them by fetching the recent posts from personal blogs across many categories. There are two versions: Minimal (HN-inspired, fast, static): https://text.blogosphere.app/ Non-minimal: https://blogosphere.app/ If you don't find your blog (or your favorite ones), please add them. I will review and approve it.
AI · Apr 2026 · text.blogosphere.app