Generative AI coding tools and agents do not work for me

Is it a skill worth learning though? How much does the output quality improve? How transferable is it across models and tools of today, and of the future?

From what I see of AI programming tools today, I highly doubt the skills developed are going to transfer to tools we'll see even a year from now.

Regarding using AI tools for programming it is not a one-for-all choice. You can pick a grunt work task such as "Tag every such and such terraform resource with a uuid" and let it do just that. Nothing to do with quality but everything to do with a simple task and not having to bother with the tedium.

Why use AI to do something so simple? You're only increasing the possibility that it gets done wrong. Multi-cursor editing wil be faster anyway.

It will very soon be the only way.

Why not? I regularly have a couple Claude instances running in the background chewing through simple yet time consuming tasks. It’s saved me many hours of work and given me more time to focus on the important parts.

  > a couple Claude instances running in the background chewing through simple yet time consuming tasks.

If you don't mind, I'd love to hear more about this. How exactly are they running the background? What are they doing? How do you interact with them? Do they have access to your file system?

Thank you!

Given I see people insisting these tools don't work for them at all, and some of my results recently include spitting out a 1k line API client with about 5 brief paragraphs of prompts, and designing a website (the lot, including CSS, HTML, copy, database access) and populating the directory on it with entries, I'd think the output quality improves a very great deal.

From what I see of the tools, I think the skills developed largely consists of skills you need to develop as you get more senior anyway, namely writing detail-oriented specs and understanding how to chunk tasks. Those skills aren't going to stop having value.

I would guess that they're running multiple instances of Claude Code [0] in the background. You can give it arbitrary tasks up to a complexity ceiling that you have to figure out for yourself. It's a CLI agent, so you can just give it directives in the relevant terminal. Yes, they have access to the filesystem, but only what you give them.

[0]: https://www.anthropic.com/claude-code

Those tasks can take hours, or at least long enough where multiple tasks are running in the background? The page says $17 per month. That's unlimited usage?

If so, it does seem that AI just replaced me at my job... don't let them know. A significant portion of my projects are writing small business tools.

> Those tasks can take hours, or at least long enough where multiple tasks are running in the background?

Maybe not hours, but extended periods of time, yes. Agents are very quick, so they can frequently complete tasks that would have taken me hours in minutes.

> The page says $17 per month. That's unlimited usage?

Each plan has a limited quota; the Pro plan offers you enough to get in and try out Claude Code, but not enough for serious use. The $100 and $200 plans still have quotas, but they're quite generous; people have been able to get orders of magnitude of API-cost-equivalents out of them [0].

> If so, it does seem that AI just replaced me at my job... don't let them know. A significant portion of my projects are writing small business tools.

Perhaps, but for now, you still need to have some degree of vague competence to know what to look out for and what works best. Might I suggest using the tools to get work done faster so that you can relax for the rest of the day? ;)

[0]: https://xcancel.com/HaasOnSaaS/status/1932713637371916341

Maybe this is yet another application of the bitter lesson. It's not worth learning complex processes for partnering with AI models, because any productivity gains will pale in comparison to the performance improvement from future generations.

With such tedious tasks does it not take you just as long to verify it didn't screw up than if you had done it yourself?

If I had a green field project that was low novelty I would happily use AI to get a prototype out the door quickly. I basically never work on those kinds of projects though, and I've seen AI tools royal screw up enough times given clear direction on both novel and trivial tasks in existing code bases.

Detailed specs are certainly a transferable skill, what isn't is the tedious hand holding and defensive prompting. In my entire career I've worked with a lot of people, only one required as much hand holding as AI. That person was using AI to do all their work.

Perhaps... Even if I'm being optimistic though there is a ceiling for just how much productivity can be gained. Natural language is much more lossy compared to programming languages, so you'll still need a lot of natural language input to get the desired output.

Describing things in enough detail that someone else can implement them is a pretty important skill. Learning how to break up a large project into smaller tasks that you can then delegate to others is also a pretty important skill.

Yeah, Claude Code. I have the $100/month Max plan. I run 3-5 instances “in the background” (just another terminal) while I work. It really helps work through the backlog of “easy-ish things that I eventually need to do, but are relatively low priority.”