On the spot generated code: LLMs and Python

Wed, 16 Jul 2025 19:18:19 +0100

Disclaimer: applying this in a real world scenario generally is a terrible idea, don’t create a startup based in this idea (unless you invite me to join)

I have been using LLMSs to genterate code for a while Somewhat like two years now. So far I have been just asking them to generate some code, copy it and the paste it to run with extremely diverse results. Next, all the big AI LLM-based companies created CLI interfaces that gets access to your filesystem and command line, and directly did the breaking changes to your codebase. This is the old way to create code with LLMs, there is a brand new unsafe way to create code, I present to you, the “on the spot generated code”, which is as expensive and unpredictable as it sounds.

Most of your code won't be on GitHub

Sat, 25 Jan 2025 19:18:19 +0100

Recently, I came across a tweet that sparked a moment of self-reflection. The tweet showcased a software engineer with a GitHub profile filled with green squares, indicating a high volume of commits. The person who tweeted mentioned sending this developer a rather lucrative job offer on the spot. After seeing this, I spent a week feeling a bit embarrassed about the state of my own GitHub profile, which was comparatively barren.

Software Development on Robles.dev

On the spot generated code: LLMs and Python

Most of your code won't be on GitHub