Hacker News Reader

Comment by carterschonwald | Hacker News Reader

idk, if anything I’m thinking more. The idea that I might be able to build everything I’ve ever planned out. At least the way I’m using them, it’s like the perfect assistive device for my flavor of ADHD — I get an interactive notebook I can talk through crazy stuff with. No panacea for sure, but I’m so much higher functioning it’s surreal. I’m not even using em in the volume many folks claim, more like pair programming with a somewhat mentally ill junior colleague. Much faster than I’d otherwise be.

this actually does include a crazy amount of long form latex expositions on a bunch of projects im having a blast iterating on. i must be experiencing what its almost like not having adhd

View on HN

Interesting. I feel like it makes my ADHD worse. If I code “manually” then I can enter hyperfocus/flow and it’s relaxing. If I use AI to code then I have to sit around waiting for it to respond and I get distracted and start something else, forgetting what I was doing before. Maybe there’s a better workflow for me though.

I don't have ADHD but I've set Codex CLI to send me a push notification via PushOver when it ends its turn and it helps a lot.

Try running multiple agents - more task switching overhead, but I find planning in one agent while another is executing is a good balance for me, and avoids the getting-distracted trap

task switching is precisely an issue with adhd though

I'm adhd as well, so I get the pain. I tend to try and do frontend / backend on a single project to at least stay within the same domain

It helps to be able to ask at inside any session at any point "yo, what were we doing and how's it going"

you gotta use faster models, this is the next big leap in agentic coding. In 2 years we will have opus 4.5 at 1000 tokens/sec and it will be glorious.

Maybe it’s not that we’re getting stupid because we don’t use our brains anymore. It’s more like having a reliable way to make fire — so we stop obsessing over sparks and start focusing on building something more important.

Instead of being the architect, engineer, plumber, electrician, carpenter you can (most of the time) just be the architect/planner. You for sure need to know how everything works in case LLMs mess the low level stuff up but it sure is nice not needing to lay bricks and dig ditches anymore and just build houses.

It won't turn most people into architects. It will turn them into PMs. The function of PMs is important but without engineers you are not going to build a sustainable system. And an LLM is not an engineer.

If you already are an engineer it frees you up to be an architect.

If you aren't, then sure you'll be a PM with a lackluster team of engineers.

LLMs can engineer small well defined functions / scripts rather well in my experience. Of course it helps to be able to understand what it outputs and prod it to engineer it just the way you want it. Still faster than me writing it from scratch, most of the time. And even if it's the same time as me doing it from scratch it feels easier so I can do more without getting tired.

And if you are already an architect - you are likely planning to start a business

It just feels like AI upskills everyone a little.

I don't think it is automatically accurate. I would be curious to learn how you arrived at that conclusion. What I seem to be seeing is that actual impact depends heavily on the person involved. Curious people dig in and even when lulled into copy/paste, they can usually snap out of it. But what do we do about those, who just want an answer, any answer..

> It won't turn most people into architects. It will turn them into PMs

That sounds awful. Every PM I've ever met, I did their job for them. They did nothing. And I've met some heavy hitter PMs with a lot of stripes and recommendations.

The job of being a PM is over-exaggerated. It boils down to writing things down and bringing them up later. Something I ended up doing for them, because they didn't know enough to know what to write down. Their skills are interviewing well and drinking beers with important people.

So what you said is a dreadful future, if true.

And side note, my last PM didn't even take notes, he had AI do it for him. They were always wrong. I had to correct them constantly.

You've described PMs running circles around you and you still can't see it. They didn't need to praise you or pressure you. They seem to have all caught on that your button is let you feel smarter than them. You did their job, did a bunch of physical typing they would otherwise have to do themselves, and walked away thinking you won.

Meanwhile they're pulling the same or greater comp, working half the hours, and "drinking beers with important people" is an accepted part of their job. The status hierarchy you're describing where they suck isn't real. It's a useful fiction that keeps you grinding while they harvested your output.

Everyone becoming a PM is a good thing precisely because PMs don't work as hard. Wouldn't a job be more pleasant if you could meet expectations by lunch? Imagine how psychologically freeing that would be. Dreadful future my ass.

Considering every time they left not a single thing changed, as though they were never there, because I was the one actually organizing the projects, I doubt they were running circles around me. Likely dicking around with Jira for 5 hours to siphon money from our company instead of actually organizing the project.

> Meanwhile they're pulling the same or greater comp, working half the hours, and "drinking beers with important people" is an accepted part of their job

You took the words right out of my mouth. Almost like it's a made up job and not the real work that needs to get done.

> Maybe it’s not that we’re getting stupid because we don’t use our brains anymore.

The study shows that the brain is not getting used. We will get stupid in the same way that people with office jobs get unhealthy if they don't deliberately exercise.

Same here re: ADHD. It's been invaluable. A big project that would have been personally intractible is now easy - even if the LLM gives slightly wrong answers 20% of the time, the important thing is that it collapses the search space for what concepts or tools I need to look into and gives an overall structure to iterate on. I tend to use ChatGPT for the big planning/architectural conversation, and I find it's also very good at sample code; for code writing/editing, Copilot has been fantastic too, lately mostly using the Opus agent in my case. It's so nice being able to delegate some bullshit gruntwork to it while I either do something else or work on architecture in another window for a few minutes.

It certainly hasn't inhibited learning either. The most recent example is shaders. I started by having it just generate entire shaders based on descriptions, without really understanding the pipeline fully, and asking how to apply them in Unity. I've been generally familiar with Unity for over a decade but never really touched materials or shaders. The generated shaders were shockingly good and did what I asked, but over time I wanted to really fine tune some of the behavior and wound up with multiple passes, compute shaders, and a bunch of other cool stuff - and understanding it all on a deeper level as a result.

I can definitely relate to the abstract at least. While I am more productive now, and I am way more excited about working on longer term projects (especially by myself), I have found that the minutia is way more strenuous than it was before. I think that inhibits my ability to review what the LLM is producing.

I haven't been diagnosed with ADHD or anything but i also haven't been tested for it. It's something I have considered but I think it's pretty underdiagnosed in Spain.

Indeed, I feel like AI makes it less lonely to work, and for me, it's a net positive. It still has downsides for my focus, but that can be improved...

Can you elaborate on how you use AI for this? Do you do it for coding or for “everything?”

I am currently writing a paper and I am thinking exactly the same.

That must be how normal people feel.

Yeah, I'd say I'm thinking and doing way more.

One of my favorite things is that I no longer feel like I need to keep up with "framework of the year"

I came up over a decade ago, places I worked were heavy on Java and Spring. Frontends were Jquery back then. Since then I've moved around positions quite a bit, many different frameworks, but typically service side rendered MVC types and these days I work as an SRE. The last 5 years I've fiddled with frontend frameworks and SPAs but never really got into it. I just don't have it in me to learn ANOTHER framework.

I had quite a few projects, all using older patterns/frameworks/paradigms. Unfortunately these older paradigms don't lend themselves to "serverless" architecture. So when I want to actually run and deploy something I've gotta deploy it to a server (or ecs task). That shit starts to cost a bit of money, so I've never been able to keep projects running very long... typically because the next idea comes up and I start working on that and decide to spend money on the new things.

I've been working at a cloud native shop the last 7 years now. Damn, you can run shit CHEAP in AWS if you know what you're doing. I know what I'm doing for parts of that, using dynamodb instead of rds, lambdas instead of servers. But I could never get far enough with modern frontend frameworks to actually migrate my apps to these patterns.

Well, now it's easy.

"Hey Claude, look at this repo here, I want to move it to AWS lambdas + apigw + cloudfront. Break the frontend out into a SPA using vue3. I've copied some other apps and patterns {here} so go view those for how to do it"

And that's just the start.

I never thought I'd get into game development but it's opened that up to me as well (though, since I'm not an artist professionally I have issues getting generative AI to make assets, so I'm stuck plodding along in aseprite and photoshop make shit graphics lol). I've got one simple game like 80% done and ideas for the next one.

I never got too far down mobile development either. But one of the apps I made it could be super useful to have a mobile app. Describe the ux/ui/user flow, tell it where to find the api endpoints, and wham bam, android app developed.

Does it make perfect code one shot? Sometimes, but not often, I'll have to nudge it along. Does it make good architectural decisions? Not often on its own, again, I'l nudge it, or even better, I'll spin up another agent to do code reviews and feed the reviews back into the agent building out the app. Keep doing that loop until I feel like the code review agent is really reaching or being too nitpicky.

And holy shit, I've been able to work on multiple things at the same time this way. Like completely different domains, just have different agents running and doing work.

I've had the same type of experience where I feel like the knowledge barrier for a lot of projects has been made much smaller than it used to be :D

btw, I have a couple of questions just out of curiosity: What tools do you use besides Claude? Do you have a local or preferred setup? and do you know of any communities where discussion about LLM/general AI tool use is the focus, amongst programmers/ML engineers? Been trying to be more informed as to what tools are out there and more up to date on this field that is progressing very quickly.

Claude is my favorite and at work it's what we officially use. At home I pay for claude by the token but I have a gemini and chatgpt account. So at home I use a lot more gemini cli and codex.

For my setup, I make sure I have good markdown files and I use beads. I'll usually have an AGENTS.md, CLAUDE.md, GEMINI.md in every project and 99.9% of the time they're the exact same. I always make sure to keep these files up to date. If the LLM does something I don't like and I can foresee it being a problem, I'll add it to the markdown file as something not to do.

My markdown files generally have multiple sections. There's always a good chunk describing the app (or in a non software case, the goal or purpose). Some design/architecture decisions will make it into the markdown files. How to build/test are in the markdown files.

I think it helps that I already have good patterns and structure to most things I build. I have moved more to a monorepo since LLMs came out. So an android app won't be in a separate repo as the webapp, instead they're all in the same repo with different directories (frontend vs {app}-android/{app}-iphone/{app}-mobile). Everything I build gets deployed to AWS and I have good patterns for that. Make for builds/deploys/tests, I don't ever run terraform or npm or maven or any other builds on the cli, if I'm running it it goes in the Makefile. All apps follow the same Makefile patterns where certain commands all get rolled up into the same one (make plan, make build, make deploy) using the same general env vars.

Now for tools and such, I feel like just the cli agents themselves are it. On personal stuff that's 100% all I use, the cli agent. At work I integrate with some MCPs and I've created and use some skills/plugins, but tbh I don't feel like they make a big difference or are necessary. I think the non-deterministic nature of the tool makes these unnecessary. Like sometimes I have to explicitly tell the agent to use the MCP. Sometimes the MCP takes up more context than having the llm create a script to hit and API and recreate the MCP's functionality.

And when I have questions, like you did here, I ask the llms first. I ask a lot of "meta" questions to the llm in my sessions even. I like to think it primes it for going down the path you want.

I feel the same. Do you think this is because the ADHD brain has so many ideas or is it the same for neuro-normal people?

Reply on news.ycombinator.com