Comment by discreteevent
1 month ago
> I'm not sure how useful it is to say this
I have to be honest and say it's not very useful for me to hear you say this because you make your living from AI consulting and in a previous thread [1] you said that you don't review the code and then that you do. I'm not saying you have psychosis but your take on AI is inconsistent and confusing to me.
Yeah, that's why I said "I'm not sure how useful it is to say this", because I know a lot of people will be a) offended by the message or b) offended that I was the one to say it.
That particular reference isn't fair though. You need to view that comment in context: https://twitter.com/bcherny/status/2098217573276131577
I'm entirely in agreement with that. The interesting challenge is how we achieve that new high bar.
I don't actually buy that tweet from Boris Cherny. When the Claude Code source leaked some months ago, there were many posts on Mastodon about how the revealed code was a shit show, a big pile of hacks. I wish now that I had bookmarked some of those posts.
Here's the one I saw most widely cited: https://neuromatch.social/@jonny/116324676116121930
I wasn't very impressed by that pile-on, personally.
Has there ever been a rapidly evolving 1,000,000+ line codebase that suitably motivated critics couldn't pick a thousand holes in and conclude that the code was garbage?
Claude Code is used by millions of people on a daily basis, has generated billions of dollars in revenue, and spits out new features on a weekly basis.
Many of the complaints I saw - things like the absurdity of asking for JSON and then looping against a schema until it matches - are common patterns for building software against language models, which are weird components to need to tame.
4 replies →