Thoughts on AI

I think most developers are feeling some level of this right now. I’m using AI extensively and it’s the most exciting thing to come along in tech for a long time. But it is scary, because it’s impossible to see where it will take us, not just in the developer community, but in the world at large.

A good amount of this is similar to my experience.

AI spending (and AI drawing available venture capital investment) is more responsible for cutbacks than AI doing the work of those who lost their jobs. As anyone who reads this knows, I believe that AI can help developers be more productive; I don’t believe that it can do developers’ jobs.

I’m using Claude Code on the Web, and it’s pretty neat so far. The option of having a few different sessions all working in parallel in the cloud, and being able to check in on their progress from mobile, is a nifty one. It’s worth checking out with the free credit until Nov. 18.

The detail on how companies are structuring the debt they’re taking on to build data centers is interesting, and scary. The financial engineering around the AI boom is all too reminiscent of other boom/bust cycles, so I guess we just have to hope to dodge the bust this time.

Looks interesting. Yet another thing to put on the list to check out.

This was one of the easiest Rails upgrades I’ve done yet. Also, since I’ve been posting about using AI agents, and here’s what deploying the newly updated app looked like.

You just _know_ Doctorow is right: we’ll be getting sold stuff by AI with little visibility in no time. It’s hard to see what the incentive structures are, and I have no doubt that moral clarity alone is not enough to deter the leaders of those companies from tapping that keg.

As part of my ongoing experiments using AI agents, I created two specialized agents that work together to automate an entire release process—from test verification through production deployment. Read more about it here.

Over the past few days, I’ve been experimenting with a new-to-me workflow: using [git worktrees](https://git-scm.com/docs/git-worktree) to let AI agents try multiple parallel implementations of the same feature. It’s been interesting enough to share.

We focus on the times when LLMs do a bad job, but since humans are deliberately doing a bad job pretty regularly, this might be a good use for the tech.