You're gonna get a lot of positive responses here, but frankly only do it if you think you can make meaningful money within a month or two.
Everything is going off the rails this year. You only have to use Claude Code for 10 minutes to realize every job involving a computer is going to get flipped upside down within a year.
Lol that's what they told us last year. And they'll say the same thing next year. It's obviously useful for certain tasks but the number of errors and hallucinations are still quite bad for anything large or complex or really novel. That part is improving very slowly and some fundamental theoretical breakthroughs will be needed.
I just keep hearing all these people that preach this, but I don't see anything substantial (that isn't something stupid or a tutorial they followed from medium) that anyone responds with. e.g. of a meh: give me top 10 HN articles for today and summarize the contents, add tags and build a website. I know AI can do that, but it's not impressive.
Not to pick on you, be mean or anything, but your github profile says no contributions in a year. Obviously there are other online git repo sites.
Care to share anything in prod? For a reply so aggressive, the proof is in the pudding.
AI is already more or less ultimately powerful with nearly endless ressources - though, no one built a big software company in the last 3 - 4 years solely with AI to replace one of the behemoths.
The fact that you own a car which could bring you everywhere does not mean that you actually will go eveywhere.
On a conference 2 month ago, one speaker claimed that AI will be so powerful that within 3 years there will be guys who replace microsoft because they have a better coding AI than today.
Have you actually had it do anything substantial and then tried to work with the code it produces afterwards? It may "work" but it's a horrific mess. Good luck bug fixing that.
Yes, with GPT 5.2 Codex and 5.2 Pro specifically. It’s not a mess because of the context I provide and the guidance and reattempts I apply. It’s working great, the resulting code is good when I accept it, and I’m getting much more done than in the before times.
Im working productive with it every day (Claude Opus). If you provide enough context, the code usually works veeeery well on first shot.
(For sure, I do not tell it "build me a facebook", instead Im telling it precisely which single function I want to have, how it should work, what the output should be.
Chunk it into single parts/components/building blocks. Then do each of these a dedicated project/workspace. In each of these workspaces, you put in only the source code relevant for this module. You are working in each project/workspace separately.
I am just as bullish as you on the potential. AI is going to change the world all right. Much bigger than the internet.
I an far, far less bullish than you on the timeframe. The vast amount of work is not even optimised for computers without AI. Much if not most bureaucratic process has stayed mostly the same for the best part of a hundred years.
It will change everything, but not in a single year!
+1. Claude is actually really good at all kinds of development but Claude will still make plenty of mistakes and occasionally go so far in the wrong direction that it still needs someone with experience to steer it.
Everything is going off the rails this year. You only have to use Claude Code for 10 minutes to realize every job involving a computer is going to get flipped upside down within a year.