Tell HN: I'm 60 years old. Claude Code has re-ignited a passion

I'm much younger, just 42, but due to other medical problems, my attention span was being reduced. I've been programming profesionally for about 25 years, but the last years I was putting myself more into other roles, because being able to focus on code for a few hours uninterrupted is a luxury that I don't have anymore. I was honestly thinking I'll have to retire early. That was until I've tried Claude Code last year. It feels like a superpower. I can guide it, I can review it, I don't need it for thinking, I need it for writing code and under very strict guidance, it does that well. I feel like this extends the years I can do software well into to the future. In a way, I welcome masses thinking AI can produce software on it's own, it gives me hopes for more earning in the future for me.

Similar story. I’m a bit younger, but Amiga BASIC/VB3/VB6/ASP/.NET was my path. There was a joy when “Visual Studio” meant “you can visually drag a component on and that is the app” instead of editing text files. But gradually we learned you need to be in the code. Sure you have figmas and low code tools today. But industry has gravitated back to editing curly brackets and markup in text files. And for good reasons I think.

I landed on GitHub Copilot. I now manage a team, but just last night snuck away to code some features. I find my experience and knowing how to review the output helps me adopt and know how much to prompt the agent for. Is software development changing? Absolutely. But it always has been. These tools help me get back to that first freedom I felt when I dragged a control onto a VB6 designer, but keep the benefits of code in text files. I can focus on feature, pay attention to UX detail, and pivot without taking hours.

Is it only possible to have success with paid versions of these LLMs?

Google's "Ask AI" and ChatGPT's free models seem to be consistently bad to the point where I've mostly stopped using them.

I've lost track of how many times it was like "yes, you're right, I've looked at the code you've linked and I see it is using a newer version than what I had access to. I've thoroughly scanned it and here's the final solution that works".

And then the solution fails because it references a flag or option that doesn't even exist. Not even in the old or new version, a complete hallucination.

It also seems like the more context it has, the worse it becomes and it starts blending in previous solutions that you explained didn't work already that are organized slightly different in the code but does the wrong thing.

This happens to me almost every time I use it. I couldn't imagine paying for these results, it would be a huge waste of money and time.

As a parent to two young kids and in more of a leadership position at work, Claude allows me to grind through my backlog of ideas in minutes between other tasks, and see which ones take flight.

Something that shifted for me: tools like Claude Code made it viable to actually run multiple agents on real long-running workflows, not just one-off scripts.

Which immediately surfaces the next problem: how do those agents communicate back to you while running?

Most setups default to tailing a log file, or a Slack/Telegram bot bolted on as an afterthought. Works for one agent. Falls apart when you have five running overnight and one hits an edge case at 2am that needs a human call.

The agent-to-human communication layer is still surprisingly ad-hoc. You can generate more ideas and actually implement them now — but the infrastructure for keeping humans in the loop as agents execute is still duct tape. Feels like the next interesting problem after the coding unlock.

I'm 51. I use codex rather than claude code. But, I sure am using it a lot. It's more or less my default at this point. I lean heavily on my decades of experience to make sure things are done right and to correct the generation process. That seems critical. You can get anything you ask for but if you don't know how to ask for the right things, it will happily create a big stinking mess instead. There's some skill to this.

I'm now dealing with a lot of stuff via codex, including technical debt that I identified years ago but never had the time to deal with. And I'm doing new projects. I've created a few CLIs, created a websites on cloudflare in a spare half hour, landed several big features on our five year old backend and created a couple of new projects on Github. Including a few that are in languages I don't normally use. Because it's the better technical choice and my lack of skills with those languages no longer matters.

I also undertook a migration of our system from GCP to Hetzner and used codex to do the ansible automation, diagnosing all sorts of weirdness that came up during that process, and finding workarounds for that stuff. That also includes diagnosing failed builds, fixing github action automation, sshing into remote vms to diagnose issues, etc. Kind of scary to watch that happen but it definitely works. I've done stuff like this for the last 25 years or so using various technologies. I know how to do this and do it well. But there's no point in me doing this slowly by hand anymore.

All this is since the new codex desktop app came out. Before Christmas I was using the cli and web version of codex on and off. It kind of worked for small things. But with recent codex versions things started working a lot better and more reliably. I've compressed what should be well over half a year of work in a few weeks.

It's early days but as the saying goes, this is the worst and slowest its ever going to be. I still consider myself a software maker. But the whole frontend/backend/devops specialization just went out of the window. But I actually enjoy being this empowered. I hate getting bogged down in grinding away at stupid issues when I'm trying to get to the end state of having built this grand thing I have in my head. There definitely is this endorphin rush you get when stuff works. And it's cool to go from idea to working code in a few minutes.

I'm only forty but ditto.

Been programming off and on since I was a kid, though I went into a career of systems architect instead, because I found the actual process of churning out code kinda tedious.

But I still had all these ideas in my head that I wanted to make reality, and now I finally can.

A project that would normally take weeks, and significantly affect the rest of my life, now only takes hours.

But remember that all those projects need to be maintained too, you can't just release a bunch of new code into the open source ecosystem without maintaining it.

I totally agree with this! I've spent a career learning and making software of all types. I started with DOS 4, worked through VB6, and so on. Now I think more broadly and my mind is always thinking of new ideas, but with a family, it's tough to find time to create some of these. I know what the software needs to do and even what it should look like. I know the acceptance criteria and what will and won't work, so Claude has been great just being an extra set of fingers. I use it to create all sorts of projects that I would never have time to make with my busy schedule, and it's so much fun!

I retired in 2024 after a four decade career, mostly programming avionics systems but with a decade of Ruby on Rails towards the end. I am now sitting here eating popcorn and watching the disaster unfold. I am happy to be out of it. So long as it doesn't affect my pensions and the local shops still have food...

I've always dabbled in electronics, as a hobbyist. I've never had any formal courseware or training in it.

But I have been haranguing Claude/Gemini to help me on an analog computer project for some months now that has sent me on a deep dive into op-amps and other electronics esoterica that I had previously only dabbled a bit in.

Along the way I've learned about relaxation oscillators, using PWM to multiply two voltages, integrating, voltage-following…

I could lean on electronics.stackexchange (where my Google searches often lead) but 1) I first have to know what I am even searching for and 2) even the EEs disagree on how to solve a problem (as you might expect) so I am still with no clear answer. Might as well trust a sometimes hallucinating LLM?

I guess I like the first point above the best—when the LLM just out of the blue (seemingly) suggests a PWM multiplier when I was thinking log/anti-log was the only way to multiply voltages. So I get to learn a new topology.

Or I'm focused on user-adjustable pots for setting machine voltages and the LLM suggests a chip with its own internal 2.45V reference that you can use to get specific voltages without burdening the user to dial it in, own a multimeter. So I get to learn about a chip I was unfamiliar with.

It just goes on an on.

(And, Mr. Eater, I only let the magic smoke out once so far, ha ha.)

I started at 16, 44M now, but also remember all that COM stuff, writing shell extensions for Windows 95 and stuff. And reading about it in the press (MSDN Magazine?). It was the new AI then ;)

I think you really hit the jackpot because you got a full career out of it, saw an amazing evolution etc. So you can hopefully enjoy the ride now being more as a spectator without the fear of being personally affected by job displacement. Enjoy the retirement!

From what I've seen, and of course the models get better everyday, if you have very simple grunt work that needs to be done. Coding agents are basically magic. The moment something gets either difficult or subjective, coding agents love to add completely incorrect solutions.

Try to tell Claude Code to refactor some code and see if it doesn't just delete the entire file and rewrite it. Sure that's cute, but it's absolutely not okay in a real software environment.

I do find this stuff great for hobbyist projects. I don't know if I'd be willing to put money on the line yet

Same energy here. I'm in my late 20s but the feeling OP describes is exactly what I got when I started using Claude Code for a fintech side project. Spent years wanting to build stuff but getting bogged down in boilerplate and config hell. Now I just describe what I want and iterate. It's like pair programming with someone who never gets tired and doesn't judge your 2am ideas.

Going from static HTML to dynamic ASP felt like suddenly gaining superpowers. We've been missing that true 'Rapid Application Development' (RAD) energy for a long time. Today’s AI agents are basically the modern incarnation of dragging and dropping a button in VB6 and writing logic behind it, but on a massive scale. It's great to hear you've found that spark again!

Thanks for sharing. It feels like you're in my head. Once people realize there's 4 layers of abstraction covering the old LAMP stacks, I think the modern architecture is going to have a hard crisis. Yes, there really will be an AI job hit, but it will be for people working on stuff that was a band aid on top of a band aid.

> I love it. It feels like it did back then. I’m chasing the midnight hour and not getting any sleep.

I highly recommend this blog post about vibe coding, gambling, and flow. Glad you're having a great time! Just something to consider.

https://www.fast.ai/posts/2026-01-28-dark-flow/

This resonates. The emotional side of returning to coding is real.

With Claude Code specifically, I've noticed that the longer it runs autonomously, the more cost anxiety creeps in. You stop thinking about the problem and start watching the token counter.

What finally let me stop worrying and just build again was building a hard budget limit outside the app — not just alerts, but an actual kill switch.

Glad you found the spark. It's worth protecting.

Here here. It's like brainstorming projects/optimizations that directly improve QoL and have a bunch of keeners do the work. Sometimes they turn in C efforts, but they're so eager you don't feel bad to tell them to start again.

I feel this so, so much. It is a very exciting time. I have had a very specific goal in mind and I could work out large parts on my own. But there is a lot that I didn't have any basis or time to build expertise on. Using Claude Code to fill out those gaps and educate me along the way has meant I've gotten little sleep in the last two months. And I managed to make the thing I was envisioning: https://gridpaper.org/examples/ :)

I’m not quite as old as you, but I am old enough to know what a COM component is and to have ready the Byte Magazine article that likely described this ancient stone tablet tech. Codex has me absolutely stoked again. I can finally have fun with the youngsters, knowing that the latest new hotness no longer has a learning curve.

For me, learning Elixir did this. I was going to change careers into commercial real estate about 9 years ago and then I binge read “Programming Phoenix” over a weekend.

Walked into work Monday morning, bleary eyed and told everybody, “This is the solution. This is how you build rapidly and bypass all of the long term maintenance issues that we always have to fix in every other codebase. It makes the hard things easy, it makes perfect sense and it’s FUN.”

I had my real-deal moment recently.

I was getting Claude to implement a popular TS drag and drop library, and asked it to do something that, it turns out, wasn't supported by the library.

Claude read the minified code in node_modules and npm patched the library with the feature. It worked, too.

Obviously not ideal for future proofing but completely mind blowing that it can do that.

Me too - I am 65 and coding all hours. At least half the time on tooling to encode the way I want to do things. I have ideas and implement them. I think it is fun as you make more progress. I do think it is a temporary phase and not sure if the next one will be as much fun or once I have drained the accumulated ideas that would be nice to do someday.

I feel selfish in that I am towards the end of my career rather than right at the start.

Can you explain why or how this works for you? I'm of a similar vintage, and what I did back in "our day" was essentially chase knowledge. With AI and CC, yes I could stay up all night but it feels a lot more like trying to finish a video game or binge-watch streaming video than discover the meaning of life.

Is this to promote Claude Code? These days, I don't know how to figure out marketing campaign vs real person.

Same here! I'm working on a simple game and I use Claude Code to make it with Phaser, and I am not a game dev. I used Claude to plan it (with a chat for 3 hours), it made a document to describe everything I wanted in the game (the spec). Next I use Claude Code to implement every aspect of the game step by step. I didn't know the framework Phaser, but after each step I review the code and learn a lot. I don't think I would have it working so fast without Claude Code. I can focus on the spec and learn the framework. I code maybe 5% of it, everything is made by Claude Code.

@shannoncc would love to read how you're using it. could you share more details?

I like theconcept of being able to quickly turn thoughts into actionable projects but I do miss the financial strain, years of study, trials and tribulations and the blood sweat and tears of the old school journey that created those life-long memories of that aha moment you spent months, if not years trying to achieve. ~Respect The Grind~

Is the focus on tools, or the product?

"Without tubes of paint, there would have been no Impressionism." - Renoir

I wonder if the pace of change in AI will push you back to the "ready to retire" state.

Sure, AI is exciting, and it reignites a passion. But everything you learn today will be obsolete a year from now. And that might tire you out again.

Great timing on this post. I’ve been working on NeoNetrek, bringing Netrek into the browser with a modernized server and 3D web client. It’s the kind of project I’d started and abandoned a few times over the years because the complexity always piled up faster than the fun. Claude changed that. The gap between “idea” and “working thing” collapsed in a way I haven’t felt since the early days. I stopped fighting infrastructure and started just building. Three decades of accumulated complexity just faded away.

It doesn’t matter where you get that passion for getting back into the swing of programming, I’m not far from your age, and truly everything becomes more monotonous over time in this life, and what was once a passion becomes something hard to achieve. In my case, AI helped me handle the tedious part of things and just kept the fun stuff of finding the solution and just tell it how to solve it, and it helps me achieve it much faster than ever before. Keep going and going! Who knows what you’ll achieve tomorrow. Keep the channel open with updates.

You are 60 and most likely retired. It’s fun and “ignited a passion” in you because are NOT doing this for a living.

Interesting bifurcation between developers that get energized by AI coding and those that feel depressed. Only one side will come out on top, even if it’s for a limited time.

Finally we learn the truth in this comment section:

  Claude is for old people!

66 here...I was a Wordpress builder rarely coding anything special, always orchestrating various favorite plugins, $1,500 here, $2,000 there, $900 work for a friend's site, etc..always wanted to not be a slave to plugins. I'm not any more!

in 1 year I built three Laravel Apps from the ground up and sold one for $18,900.

That's my story and I'm sticking to it! I love Claude!

It's a lot of fun. I'm also an old timer.

I think it's also somewhat addictive. I wonder if that's part of what's at play here.

A coworker that never argues with you, is happy to do endless toil... sometimes messes up but sometimes blows your mind...

The "experience as the real asset" point resonates deeply. I've been building agent orchestration systems and the difference between junior and senior use of AI tools is stark.

Juniors prompt "build me X" and get frustrated when it goes sideways. Seniors architect the constraints first - acceptance criteria, test harness, API boundaries - then let the AI fill in mechanical work.

The real shift: AI makes the cost of prototyping near-zero, which paradoxically makes taste and judgment MORE valuable. When you can spin up 5 approaches in a weekend, knowing which one to actually ship becomes the bottleneck.

The folks who defined their value as "typing code" will struggle. The folks who defined their value as "knowing what to build and how to verify it works" are thriving.

As a business/product person it's pretty addictive (gotta watch the token spend!). This week with a few workmates we had an idea in a pub, on train back I wrote a short spec and fired up some agents to start building. The next day, by evening, whist doing our day jobs we had a functional application working, not a poc. Few years ago this would be unthinkable.

AI is incredibly exciting. If you are the one in charge, and you can exactly determine how you use it. I don't think AI is much fun for anyone with a brain and a boss.

I remember getting my first PC. I was up all night and the next until I had read every word that was in that computer. These words of yours are exactly how I feel! It kept me up nights trying to absorb it all. Fast forward decades and Claude Code is giving me that same energy and drive. I love it. It feels like it did back then. I’m chasing the midnight hour and not getting any sleep.

Same! After years in engineering management I'm building so many small side projects thanks to Claude Code. I'm creating at a breakneck pace. Claude Code has mostly raised the level of abstraction so I can focus much more on the creative aspect of building which has been so much fun.

There are definitely a lot of limitations with Claude Code, but it's fun to work through the issues, figure out Claude's behavior, and create guardrails and workarounds. I do think that a lot of the poor behavior that agents exhibit can be fixed with more guardrails and scaffolding... so I'm looking forward to the future.

Yup, 73 here. I'm using it to build how to domain I bought back in 1997. During the dot com boom I had grand ambitions for the domain. I could have been a millionaire had I stuck with it but unfortunately life got in the way, children born, career, physical stuff, family, and my career as a reservist. All of that kept me busy. But now I'm running multiple agents everyday to build out this domain. It's working really well. Actually working out the product market fit right now. With customer outreach and etc trying to figure out what I can still do with it. It's working! Customers are responding positively. I am highly encouraged that the dream I had. But the dream I was just going to leave to my children. Might be something that could actually support me in my old age. Of course 73 is the new 43 because we're all going to live to be 150 now. Anyway I'm having a blast with it whether I succeed or not. Nobody's going to tell me that some form of AGI isn't here already. Nobody. This thing I'm dealing with every day is sentient. You don't think so I don't want to hear from you.

It’s killed mine

As a solo dev, using LLMs for coding has made me a better programmer for sure!

I can ask an LLM for specific help with my codebase and it can explain things in context and provide actual concrete relevant examples that make sense to me.

Then I can ask again for explanations about idiomatic code patterns that aren't familiar for me.

Working on my own, I don't get that feedback and code review loop.

Working with new languages and techniques, or diving into someone else's legacy code base is no longer as daunting with an LLM to ask for help!

Getting claude to build mathematical models for me and running simulations really got me back into doing sciency things too. It's the model that's important, not the boilerplate each time!

Do you think it's doing the same thing for younger generations? How are they inspired by tech? I'm an old man too, but old man stories don't really matter. What matters is what we leave behind, how well understood it will be by who comes after.

I've also been loving the speed Claude has enabled me to move at, and now agree that the coding part of SWE has become LLM-wrangling instead. I now see interacting with an LLM, to build all parts of software, as the new "frontend".

Following this idea, what do people think "backend" work will involve? Building and tweaking models, and the infra around them? Obviously everyone will shift more into architecture and strategy, but in terms of hands-on technical work I'm interested in where people see this going.

[dead]