At a shitty company. The problem is - you cannot ship a large amount of code quickly in a perfect way. Positioning the problem as "what's the point of generating all this code so fast if I still need a warm body at the end making sure it's OK?" is hilarious.
Don't do that. Just ship it. Yes, good tests, linting, etc will help but if you really believe you don't need humans in the loop at all, at least for the time being, you are fucked.
But go ahead, buy the hype. Your agent swarm can build an operating system in 15 minutes and everything will just work. Cool.
I have mixed feelings but echo your sentiments a bit. On the one hand, I can get a lot more done and feel "unchained" so to speak. I have long hated doing frontend development and now it doesn't matter and I love that. However, I don't feel satisfaction from solving problems the same way I used to. I had one long session with Claude a few weeks ago and I told Claude I was done for the night at which point it fired back with "Sounds good, look at how much you accomplished." and I responded with you mean "look at how much you accomplished, I just told you what to do."
It is still weird to me that I talk to a remote Python app but that's how we write code nowadays. Still, I felt almost mocked when Claude plauded my "accomplishments".
So I'd say that I am definitely more productive than I used to be but I enjoy the work less on one level. But on another level, I feel like I can build a lot more and tackle problems I wouldn't have tackled in the past. It's a mixed blessing. It's also a WIP, I expect that the way we write code will change even more, over the next few years.
I love it, I hate it, it's the Brave New World of software development.
I just started using Linear, it is AI native/friendly and a million effing times less bloated than Jira. So long Jira. And I say that as an old shit who migrated from Bugzilla to Jira a long time ago and I remember how refreshing Jira felt at the time.
Git is better in some ways, but it is insanely complicated. That matters less now with AI tooling but still there was a time when we all had many choices (commercial and open source) for source control tools. My canonical example is git checkout -b <branch_name> for a new branch, git branch -D <branch_name> to delete the local branch and git push origin :<branch_name>.
I know that that is the old syntax but holy hell, that's insane. Why couldn't it always have been git branch --create|delete|delete-remote? It could have but Linus doesn't care about your feelings or small brain. :)
Yeah, exactly. There is no way Claude could do that much work in one hour, starting from scratch. You can even ask Claude if it could do that and it will say the same.
The LLM/AI tools are powerful and have a ton of use cases unlike technologies like crypto, but the hype train is running full steam and no one really knows where things will land over the next 5-10 years.
There's a crazy amount of hype, fear and blatant lies in the mix. And the pace is absolutely bonkers. The pace of announcements is even more bonkers. Maybe things will settle down to a new normal at some point.
You might think that everyone has FOMO or is an anti-AI Luddite when of course there are a LOT of us somewhere in the middle, just trying to get our work done and trying to figure out what our careers will look like in 5-10 years.
One big thing that no one seems to talk about - GenAI is unlocking many new (and oftentimes "small") business ideas that were not practical just a few years ago. I have witnessed this firsthand. . . however, it will also take away jobs. How many, who knows?
tl;dr everyone is full of shit or selling something or terrified to the point where they can't think straight. And no one has a crystal ball.
I'm not convinced that the success and momentum of Claude Code will catch on with the general public. This feels like the one trick pony that's been groomed and billed as a racehorse. Or put another way Claude Cowork feels like Claude Code for people who don't code and are not interested in vibe coding.
reply