DEDUPED Hot AI repos, turned into use cases Get the Monday 5

How to unfreeze hand-written weights and train them with Handwired

Try the README's ideas: unfreeze a program's weights, or attach a frozen program to a neural net.

Short answer: Run the demos with bun start; then read docs/ and template/ to see how a program is expressed; Unfreeze the weights and train them, which the README calls an experiment to find out what it does. All steps.

Who it is forAn ML tinkerer who likes odd experiments.

The problemNormal nets start random, while Handwired starts from exact weights written by hand.

The outcomeYour own experiment, with trained weights that began as a working program.

What you need first

  • Bun to run the demos locally
  • A browser for the live demos; WebGPU is optional

Steps

  1. Run the demos with bun start
  2. Read docs/ and template/ to see how a program is expressed
  3. Unfreeze the weights and train them, which the README calls an experiment to find out what it does
  4. Or attach a specific frozen program to a generic neural net and train end to end

Prompt for your agent

Using chenglou/handwired, take the template program, unfreeze its weights and train them on a small task. Report what changes in behavior.

Caveat. The README presents these as fun experiments, so expect rough edges.

Use this in your AI agent

Ask your agent

Using the Deduped MCP, get the setup steps for chenglou/handwired and "Unfreeze hand-written weights and train them"

Add Deduped to Claude Code once

claude mcp add --transport http deduped https://dedupedai.com/mcp

Cursor, ChatGPT, others

Share: X LinkedIn Hacker News Email Copy link

Third-party repos we don't own. AI-written use cases can be wrong. Disclaimer