How to build a coding agent
It's not that hard to build a coding agent. 300 lines of code running in a loop with LLM tokens. You just keep throwing tokens at the loop, and then you've got yourself an agent.
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.
Visit ghuntley.com → RSS feedOn Hacker News Feb 2021 – Oct 2026
Software Engineering 4Life, Learning & Writing 3Tools & Productivity 2Security & Privacy 2AI & Machine Learning 2Systems & Performance 1
It's not that hard to build a coding agent. 300 lines of code running in a loop with LLM tokens. You just keep throwing tokens at the loop, and then you've got yourself an agent.
A couple of moments ago, I finished reading the article by Rob O'Leary about the pervasive data collection done by Visual Studio Code. Whilst Visual Studio Code is "open-source" (as per the OSD) the value-add which transforms the editor into anything of value ("what people actually refer
These LLMs are shockingly good at deobfuscation, transpilation and structure to structure conversions. I discovered this back around Christmas where I asked an LLM to make me an Haskell audio library by transpiling a rust implementation. An “oh fuck” moment in timeOver the Christmas break I’ve been critically looking
🔎I authored this blog post whilst I was an employee of Gitpod for Gitpod. I no longer work at Gitpod. In what seems like a long time ago, in part because it is, I learned the catastrophic capabilities of this command the hard way, and I'm sure folks my