Egregoros · Phoenix Framework

Nolan Lawson

@nolan@toot.cafe

toot.cafe admin, dev at Socket. Creator of https://pinafore.social. Formerly Salesforce and Microsoft Edge. The web is for everyone.

Posts

Followers

Following

Posts

Latest notes

Nolan Lawson

@nolan@toot.cafe remote

I think what a lot of AI critics are missing is that they're judging an LLM by its first draft. This is *not* what terrifies me about these machines.

What terrifies me is that you can ask them "find bugs in this PR." Or "find performance flaws." Or really anything.

Then have 3 agents (with different models ideally) vote on the result. Then have another fix it. Repeat until all bugs are clean.

If you haven't tried this experiment then you haven't reached the dark night of the soul that I have.

Nolan Lawson

@nolan@toot.cafe remote

My first rule for reviewing vibecoded PRs: if I can type "find bugs in this PR" into Claude and it finds bugs, then you should have done that, not me.

Nolan Lawson

@nolan@toot.cafe remote

New post: "You had a story" https://nolanlawson.com/2026/02/18/you-had-a-story/

I'm still exploring this topic, but this time through the lens of fiction (kinda).

Nolan Lawson

@nolan@toot.cafe remote

11w

"Code is cheap. Show me the talk" by Kailash Nadh https://nadh.in/blog/code-is-cheap/

This might be the single best article I've read about the impact of LLMs on coding. The good, the bad, the ugly, the absolute unrelenting horror of how everything is changing so fast.