8000 GitHub - ghuntley/ghuntley: g'day πŸ‘‹ Β· GitHub
[go: up one dir, main page]

Skip to content
7FFF
ghuntleyPublic

About

g'day πŸ‘‹

Resources

Stars

0 stars

Watchers

0 watching

Forks

Latest commit

Β 

History

15 Commits

Folders and files

NameName
Last commit message
Last commit date
Β 
Β 

Repository files navigation

Views

g'day, i'm geoff πŸ‘‹

I spend my days pondering the ponderoos about using AI in unhinged ways, and then verifying the outcomes at @antithesishq.

I'm a software engineer who writes about AI-assisted software development.

I created the Ralph loop, which runs a coding agent in a loop until the work is done. It's the technique loop engineering grew out of and defined agent back pressure: a technique for letting compilers, tests, and type checkers push back on an agent's output so it corrects itself.

I write from Kangaroo Island, Australia 🦘 at ghuntley.com.


πŸ” Ralph

  • how-to-ralph-wiggum: the Ralph Wiggum Technique. while :; do cat PROMPT.md | agent ; done, plus everything I've learned about running that loop well.
  • cursed: πŸ’€ a programming language built by Ralph. Programming, but make it gen z.

πŸ› οΈ Build your own agent

  • how-to-build-a-coding-agent: a workshop where you build a coding agent from scratch. Once you see how it works, the magic goes away and you get better at driving the tools.

🧰 Things I've shipped recently

  • overalls: [experimental] an AI-first developer platform that you own. Launches 3 November 2026.
  • underclass: an OpenAI-compatible pooling proxy that keeps prompt caches warm and cools down exhausted subscriptions.
  • preflight: a local proxy that scans LLM requests and attachments for secrets before they reach the model.

🚨 Public service announcements

  • noyaml.com: no body wants to write YAML. A lovingly curated list of YAML pain.

blog x youtube email

Usage of AI in the profession of software engineering is no longer optional. The world lacks curious, ambitious people. That's your edge; that's your alpha. Be way more ambitious than you are right now. You need to think bigger.

β€” if your team is too busy doing their 'normal job' to experiment with AI, you're preparing them to be replaced

About

g'day πŸ‘‹

Resources

Stars

0 stars

Watchers

0 watching

Forks

Releases

Packages

Used by

Contributors

0