Vibe coding
- Building software with an LLM without reviewing the code it writes
Sergej Chodarev (sergejx.net)
Ignore the “AGI” hype—LLMs are still fancy autocomplete. All they do is predict a sequence of tokens—but it turns out writing code is mostly about stringing tokens together in the right order, so they can be extremely useful for this provided you point them in the right direction.
If you assume that this technology will implement your project perfectly without you needing to exercise any of your own skill you’ll quickly be disappointed.
— Simon Willison: Here’s how I use LLMs to help me write code
The effect is predictable: finding work if your skill level is low becomes more difficult. However, if you are a highly skilled individual, you can eliminate much of the boilerplate work and focus on what matters. Thus, elite people are going to become even more productive.
— Daniel Lemire: How helpful is AI?
We ran a randomized controlled trial to see how much AI coding tools speed up experienced open-source developers.
— METR (@METR_Evals) July 10, 2025
The results surprised us: Developers thought they were 20% faster with AI tools, but they were actually 19% slower when they had access to AI than when they didn't. pic.twitter.com/w8LSTpCFZL
Everyone assumes the best AI coding workflow is: let AI generate V1, then maintain it by hand.
— Kenneth Reitz (@kennethreitz42) April 12, 2026
I'm finding the opposite works better. Write the first version yourself — pour your taste and instincts into it. Then let AI handle the features, cleanup, and maintenance.
A…
Post by @kevlin@mastodon.socialView on Mastodon
The job of a software developer is not (just) to churn out code and features. We need to create code that demonstrably works, and can be understood by other humans (and machines), and that will support continued development in the future.
— Simon Willison: Here’s how I use LLMs to help me write code
Think! About Your Work
Turn off the autopilot and take control. Constantly critique and appraise your work.