Right now I have 8 agents open in my terminal and I know I'm on the more-sceptic end of AI users. Some folks here pull thousands of lines of changes, day after day.

With this many agents I don't even have time to read what they output, not talking about the code - just their output. My work today has been (sadly) degraded to: 1. Ask AI to explore the repo. 2. Pick a solution that works for the 3 solutions that AI proposed. 3. Maybe do few rounds of follow ups. 4. Create PRs. 5. Ask agent to verify if everything works post merge.

Some of my colleagues apparently skim through the code. I pretty much don't look at the code anymore.

It's just sad. I'm self taught programmer, hobbyist. I always liked working on my stuff and always were trying to deliver high quality. I no longer can't say that, despite my best efforts.

I literally have tasks right now where not only I don't understand what the agent is doing, I don't fully understand the problem either. I could invest time to understand it and agents do a pretty good job themselves, but remember, I don't read the damn output.

That said, I work in the infra team, not in the product team, so there's that.

The perf is meh, but tbh if you look at the kind of code we, regular developers write for work, it's probably still vastly better.

Of course then there's the maintenance - updating operators, Kubernetes, whatever else you have, but you don't have to do it and if you want to do keep up with recent versions then it's just as much work as on Ubuntu or any other distro. The upside with k8s is that you can definitely roll back (I'm just assuming you're using GitOps).

Besides, you'll probably want to add all of that Kubernetes functionality at some point anyway - eg you may just at first deploy your server/app via ClickOps, have some issue, decide GitOps is the way to go, then decide that you really need to have automatic certs, then decide that DB backups would be good to have. With Kubernetes you just keep extending it and never really have to "rethink" the approach cos it's really difficult to shoot yourself in the foot unless you really want to and have a shred of understanding (and to clarify I'm speaking about small deployments), and of course because you're using it yourself your knowledge grows meaning that your expertise grows.

But I found funny that the OP summarized to use Kubernetes when CTO is no longer the only dev.

This time - I'm so close! I probably need few more weeks to somewhat polish the game and fix the rendering quirks and I'll be ready to put it online for easy access when I'm bored lol.

I’m NOT the creator.

Comments URL: https://news.ycombinator.com/item?id=48433186

Points: 4

# Comments: 1

I have zero experience building computers - where would I even start? I mean, aside from the things already well documented and mentioned in the blog post.

The simplest way to start probably would just be to create a custom Helm chart and define what you want in `values.yaml`.

- Go - backend + CLIs

- TypeScript - fronted, occasionally zx for more complex scripts

- Nushell as my scripting language (I’ve been relentlessly using it everywhere I can instead of bash/zsh and man it is such an improvement)

I heard so much good stuff about both Zig and Rust and would love to eventually get to know one of them.