Hey, I'm nearly 80 years old. I haven't written a line of code in over 10 years. But I'm coding now, with the help of Claude & Gemini, and having a great time. Each block of Python or Applescript that they generate for me is a much better learning tool than a book - I'm going through the code line by line and researching everything. And I'm also learning how to deal with LLMs and their strengths & weaknesses. Correcting them from time to time when they screw up. Lots of fun.
It's cool to rediscover Applescript for me (I'm late 40's) but it's a funny thing where I can like smell the NeXT in it almost nostalgically but it's quite handy in this new era of hijacking mac mini's (OpenClaw obviously is one way to do it, but why not just straight to the core).
I personally think coders get better with age, like lounge singers.
Same here - it's like programming with a couple of buddies. Occasionally they goof off and wreck everything, but we put it back together and end up with a finished project. I'm literally going through my backlog of projects from the early 80s! There are parts of each of these projects that were black holes for me - just didn't know enough to get a toe hold. With Karl (that's my agent) he explains everything I don't understand, does stuff, breaks stuff, and so on. It's really a blast.
This comment about the OpenClaw guy hits a little too close to home:
“Peter Steinberger is a great example of how AI is catnip very specifically for middle-aged tech guys. they spend their 20s and 30s writing code, burn out or do management stuff for a decade, then come back in their late 40s/50s and want to try to throw that fastball again. Claude Code makes them feel like they still got it.”
Same but for me it's 25 years of accumulated personal backlog that I'm finally burning through. Like I've been a project hoarder and now I have a house elf to tidy up and do all that widget fobbering business. I just need to figure out what the rules of the house are.
This describes me nearly perfectly. Though I didn’t exactly burn out of coding, I accidentally stumbled upon being an EM while I was coding well and enjoying. But being EM stuck so I got into managing team(s) at biggish companies which means doing everything except one that I enjoy the most which is coding.
However now that I run my own startup I’m back to enjoying coding immensely because Claude takes care of grunt work of writing code while allowing me to focus on architecture, orchestration etc. Immense fun.
As a principal engineer I feel completely let down. I've spent decades building up and accumulating expert knowledge and now that has been massively devalued. Any idiot can now prompt their way to the same software. I feel depressed and very unmotivated and expect to retire soon. Talk about a rug pull!
My experience is that people who weren't very good at writing software are the ones now "most excited" to "create" with a LLM.
Same here, although hopefully won't be retiring soon.
What's missing from this is that iconic phrase that all the AI fans love to use: "I'm just having fun!"
This AI craze reminds me of a friend. He was always artistic but because of the way life goes he never really had opportunity to actively pursue art and drawing skills. When AI first came out, and specifically MidJourney he was super excited about it, used it a lot to make tons and tons of pictures for everything that his mind could think of. However, after awhile this excitement waned and he realized that he didn't actually learn anything at all. At that point he decided to find some time and spend more time practicing drawing to be able to make things by himself with his own skills, not by some chip on the other side of the world and he greatly improved in the past couple of years.
So, AI can certainly help create all the "fun!!!" projects for people who just want to see the end result, but in the end would they actually learn anything?
> My experience is that people who weren't very good at writing software are the ones now "most excited" to "create" with a LLM.
I've been a tech lead for years and have written business critical code many times. I don't ever want to go back to writing code. I am feeling supremely empowered to go 100x faster. My contribution is still judgement, taste, architecture, etc. And the models will keep getting better. And as a result, I'll want to (and be able to) do even more.
I also absolutely LOVE that non-programmers have access to this stuff now too. I am always in favor of tools that democratize abilities.
Any "idiot" can build their own software tailored to how their brains think, without having to assemble gobs of money to hire expensive software people. Most of them were never going to hire a programmer anyway. Those ideas would've died in their heads.
I consider myself very good at writing software. I built and shipped many projects. I built systems from zero. Embedded, distributed, SaaS- you name it.
I'm having a lot of fun with AI. Any idiot can't prompt their way to the same software I can write. Not yet anyways.
I grew up without a mentor and my understanding of software stalled at certain points. When I couldn’t get a particular os API to work, in Google and stack overflow didn’t exist, and I had no one around me to ask. I wrote programs for years by just working around it.
After decades writing software I have done my best to be a mentor to those new to the field. My specialty is the ability to help people understand the technology they’re using, I’ve helped juniors understand and fix linker errors, engineers understand ARP poisoning, high school kids debug their robots. I’ve really enjoyed giving back.
But today, pretty much anyone except for a middle schooler could type their problems into a ChatGPT and get a more direct answer that I would be able to give. No one particularly needs mentorship as long as they know how to use an LLM correctly.
Today every single software engineer has an extremely smart and experienced mentor available to them 24/7. They don't have to meet them for coffee once a month to ask basic questions.
That said, I still feel strongly about mentorship though. It's just that you can spend your quality time with the busy person on higher-level things, like relationship building, rather than more basic questions.
As a Principal SWE, who has done his fair share of big stuff.
I'm excited to work with AI. Why? Because it magnifies the thing I do well: Make technical decisions. Coding is ONE place I do that, but architecture, debugging etc. All use that same skill. Making good technical decisions.
And if you can make good choices, AI is a MEGA force multiplier. You just have to be willing to let go of the reins a hair.
> As a principal engineer I feel completely let down. I've spent decades building up and accumulating expert knowledge and now that has been massively devalued. Any idiot can now prompt their way to the same software. I feel depressed and very unmotivated and expect to retire soon. Talk about a rug pull!
Really?
The vibe coders are running into a dark forest with a bunch of lobsters (OpenClaw) getting lost and confused in their own tech debt and you're saying they can prompt their way to the same software?
Someone just ended up wiping their entire production database with Claude and you believe that your experience is for nothing, towards companies that need stable infrastructure and predictability.
Cognitive debt is a real thing and being unable to read / write code that is broken is going to be an increasing problem which experienced engineers can solve.
What I keep hearing is that the people who weren't very good at writing software are the ones reluctant to embrace LLMs because they are too emotionally attached to "coding" as a discipline rather than design and architecture, which are where the interesting and actually difficult work is done.
IMHO any idiot can create a piece of crap.
It takes experience to create good software.
Use your experience Luke! Now you have a team of programmers to create what ever you fancy! Its been great for me, but I have only been programming C++ for 36 years.
No offense but you sound more like a “principle coder”, not a principle engineer. At least in many domains and orgs, Most principal engineers are already spending most their time not coding. But -engineering- still take sip much or most of their time.
I felt what you describe feeling. But it lasted like a week in December. Otherwise there’s still tons of stuff to build and my teams need me to design the systems and review their designs. And their prompt machine is not replacing my good sense. There’s plenty of engineering to do, even if the coding writes itself.
I spent the last 2 days primarily using Claude instead of coding things myself at work. I felt the exact opposite way. It was so unfulfilling. I’d equate it to the feeling of getting an A on a test, knowing I cheated. I didn’t accomplish anything. I didn’t learn anything. I got the end result with none of the satisfaction and learned nothing in the process.
I’m probably going to go back and redo everything with my own code.
That's interesting. I have been thinking about how the vastly different reactions people seem to have to agentic coding could be influenced by what they value about coding. To me it seems like there are three joys in coding:
1. Creating something
2. Solving puzzles
3. Learning new things
If you are primarily motivated by seeing a finished product of some sort, then I think agentic coding is transcendent. You can get an output so much quicker.
If your enjoyment comes from solving hard puzzles, digging into algorithms, how hardware works, weird machine quirks, language internals etc... then you're going to lose nearly all of that fun.
And learning new things is somewhere in the middle. I do think that you can use agentic coding to learn new technologies. I have found llms to be a phenomenal tool for teaching me things, exploring new concepts, and showing me where to go to read more from human authors. But I have to concede that the best way to learn is by doing so you will probably lose out on some depth and stickiness if you're not the one implementing something in a new technology.
Of course most people find joy in some mix of all three. And exactly what they're looking for might change from project to project. I'm curious if you were leaning more towards 2 and 3 in your recent project and that's why you were so unsatisfied with Claude Code.
I'll add "craftsmanship". It isn't just delivering "A" finished product, you want to deliver a "good", if not "the best", finished product.
I guess if you're in an iterative MVP mindset then this matters less, but that model has always made me a little queasy. I like testing and verifying the crap out of my stuff so that when I hand it off I know it's the best effort I could possibly give.
Relying on AI code denies me the deep knowledge I need to feel that level of pride and confidence. And if I'm going to take the time to read, test and verify the AI code to that level, then I might as well write most of it unless it's really repetitive.
I don't think AI coding means you stop being a craftsman. It is just a different tool. Manual coding is a hand tool, AI coding is a power tool. You still retain all of the knowledge and as much control over the codebase as you want, same with any tool.
It's a different conversation when we talk about people learning to code now though. I'd probably not recommend going for the power tool until you have a solid understanding of the manual tools.
That's a really good point. And I agree that kind of confidence in craftsmanship is something that's missing from agentic coding today... it does make slop if you're not careful with it. Even though I've learned how to guide agents, I still have some uneasiness about missing something sloppy they have done.
But then it makes me ask if the agents will get so good that craftsmanship is a given? Then that concern goes away. When I use Go I don't worry too much about craftsmanship of the language because it was written by a lot of smart people and has proven itself to be good in production for thousands of orgs. Is there a point at which agents prove themselves capable enough that we start trusting in their craftsmanship? There's a long way to go, but I don't think that's impossible.
I'm squarely into #1, but it usually requires #2 (at a high level) and has #3 as a side effect. But there's also #0 which kicks it all off: the triggering problem/question.
Like just yesterday I started to notice the increasing pressure of an increasingly hard-to-navigate number of Claude chats. So I went searching for something to organize them. I did find an extension, but it's for Chrome, and I'm a Firefox person, so I had Claude look at it with the initial idea of porting to Firefox. Then in the analysis, Claude mentioned creating an extension from scratch, and that's what I went for.
I've never really used JavaScript, let alone created a Firefox extension before, but in a few minutes I was iterating on one, figuring out how I wanted it to work with Claude, and now I have a very nice and featureful chats organizer. And I haven't even peeked at the code. I also now have a firm idea of this general spec of how I want arbitrary list-organizing UI to look+behave going forward.
I can see where this idea is coming from, but I don't agree with the conclusion at all. As someone who loves solving puzzles and learning new things, AI has been a godsend. I also very much like creating things, but even more than that, I like doing all three at once.
I think of AI like a microdose of Speed Force. Having super speed doesn't mean you don't like running; it just means you can run further and more often. That in turn justifies a greater amount of time spent running.
Without the Speed Force, most of the time you were reliant on vehicles (i.e. paying for third-party solutions) to get where you needed to go. With the Speed Force, not only can you suddenly meet a lot more of your transportation needs by foot, you're able to run to entirely new destinations that you'd never before considered. Eventually, you may find yourself planning trips to yet unexplored faraway harsh terrains.
If your joy in running came from attempting to push your biological physical limits, maybe you hate the Speed Force. If you enjoy spending time running and navigating unfamiliar territory, the Speed Force can give you more of that.
Sure, there are also oddballs who don't know how to run, yet insist on using the Speed Force to awkwardly jump somewhere vaguely in the vicinity of their destination. No one's saying they don't exist, but that's a completely different crowd from experienced speedsters.
> If you are primarily motivated by seeing a finished product of some sort, then I think agentic coding is transcendent
As someone who enjoys technology, and using it, and can just barely sort-of code but really not, agentic coding must be wonderful. I have barely scratched the surface with a couple of scripts. But simply translating "here's what I want, and how I would have done it the last time I used Linux 20 years ago, show me how to do it with systemd" is so much easier than digging through years of forum posts and trying to make sure they haven't all been obsoleted.
None of it is new. None of it is fancy. I do regret that people aren't getting credit for their work, but "automount this SMB share from my NAS" isn't going to make anyone's reputation. It's just going to make my day easier. I really did learn enough to set up a NAT system to share a DSL connection with an office in the late 1990s on OpenBSD. It took a long time, and I don't have that kind of free time anymore. I will never git gud. It's this, or just be another luser who goes without.
I think I'd add a #4 to this list, and that's helping people. I like making things that people can use to make their life easier. That's probably my number one.
The "creating something" idea... That's more complex. With agentic coding something can be created, but did I create it? Using agentic coding feels like hiring someone to do the work for me. For example, I just had all the windows in my house replaced. A crew came out at did it. The job is done, but I didn't do anything and felt no pride or sense of accomplishment in having these new windows. It just happened. Contrast that to a slow drain I had in my bathroom. I took the pipes apart, found the blockage, cleared it out, and reassembled the drain. When I next used the sink and the water effortlessly flowed away, I felt like I accomplished something, because I did it, not some plumber I hired.
So it isn't even about learning or solving puzzles, it's about being the person who actually did the work and seeing the result of that effort.
Yes! Good points! I think what I meant for point 1 was more "outputting something" vs "creating something". In my mind that encompasses materializing something into the world to achieve whatever you wanted, whether you were aiming to help others, solve a problem you alone have, or scratch some other sort of itch. It's about achieving some end. And helping somebody can be achieved indirectly and still be satisfying.
The inherent value of creating is something I was missing. Solving puzzles might be part of that, but not all. It's the classic Platonic question about how we value actions: for their own sake, for their results, or for both.
I think we agree that coding can be both, and it sounds like you feel the value for its own sake is lackluster in agentic coding -- It's just too easy. And I think that's the core sliding scale: Do you value creation more for its own sake or for its results? Where you land on that spectrum probably influences how people feel about agentic coding.
That being said, I also think that agentic coding can give enough of a challenge to scratch the itch of intrinsic value of creating. To a certain degree I think it's about moving up the abstraction chain to work more on architecture and product design. Those things can be fun and rewarding too. But fundamentally it's a preference.
It's kind of a weird thing. I spent 2 days working one some code, which in a way was the process of working out the requirements and functionality that was required. I then told Claude to look at it in and refactor it.
I did put in 2 days of work to come up with what Claude used to ultimately do what it did... but when I look at the resulting code, I feel nothing. Having the idea isn't the same as being the one who actually did the thing. I plan to delete the branch next week. I don't want to maintain what it did, and think it should be less complex than it made it.
I think your comment really captures some of the reasons behind the differences between people’s reactions to Claude pretty well.
I will add though, on 2 and 3, during most of the coding I do in my day job as a staff engineer, it’s pretty rare for me to encounter deeply interesting puzzles and really interesting things to learn. It’s not like I’m writing a compiler or and OS kernel or something; this is web dev and infra at a mid sized company. For 95% of coding tasks I do I’ve seen some variation already before and they are boring. It’s nice to have Claude power through them.
On system design and architecture, the problems still tend to be a bit more novel. I still learn things there. Claude is helpful, but not as helpful as it is for the code.
I do get the sense that some folks enjoy solving variations of familiar programming puzzles over and over again, and Claude kills that for them. That’s not me at all. I like novelty and I hate solving the same thing twice. Different tastes, I guess.
When it comes to writing code, I can almost tell before writing code that whether this particular piece of code will be intellectually stimulating to me. If so, I write it myself without thinking about whether Claude might have done it faster. If not, I let Claude write it. Currently I'd estimate maybe 70% of the code falls in the first category, and the remaining 30% is something I would've used a lot of my own willpower to get started anyways.
Also, when I write code myself, I still ask Claude to review it. It's faster than asking a human colleague to review it, so you can have Claude review often. Just today after a five-minute review Claude said a piece of code I wrote had four bugs, three of which were hallucinations and one was a real bug. I honestly do think it would have taken me a bit more than five minutes to find that one real bug.
The creator of OpenClaw had a great line about this:
"If your identity is tied to you being an iOS developer, you are going to have a rough time. But if your identity is 'I'm a builder!' it is a very exciting time to be alive."
Plus, there is no rule that says you can't keep coding if it's faster for you and/or it's quicker in general. e.g I can write a Perl one liner much faster than Claude can. Heck, even if it's not faster and you enjoy coding, just keep coding.
I'm a few years younger than the OP, but I remember the early Internet days. I started with Perl CGI scripts, ASP, even some early server side JS, in the form of Netscape Livewire.
Over the past couple months, I've created several applications with Claude Code. Personal projects that would've taken me weeks, months, or possibly forever, since I generally get distracted and move on to something else. I write pretty decent specs, break things into phases, and make sure each phase is solid before moving on to the next.
I have Claude build things in frameworks I would've never tried myself, just because it can. I do actually look at the code. Some of it is slop. In a few cases, it looks like it works, but it'll be a totally naive or insecure implementation. If I really don't like how it did something, I'll revert and give it another attempt. I also have other AIs review it and make suggestions.
It's fun, but I ultimately gain little intellectual satisfaction from it. It's not like the old days at all. I don't feel like I'm growing my skill set. Yes, I learned "something", but it's more about the capabilities of AI, not the end result.
Still, I'm convinced this is the future. Experienced developers are in the best position to work with AI. We also may not have a choice.
You're paid by a company to create software, so they can use it to drive business value and make a profit. You did so effortlessly. But it didn't make you feel personally fulfilled. So you're going to go back and re-do it, so you feel better?
How do you think your company's CEO is going to feel when you tell them you could be finishing the software much faster, but you'd rather not, because it feels better to do it by hand?
I disagree. I need to be able to support what I ship and answer to the details of what it does and why it does it. I can only truly do that if I write it myself.
There should also be a symbiotic relationship at a job. Yes, they get something from me, but I should also get something… learning and some amount of satisfaction… in addition to the paycheck. I can get a paycheck anywhere.
It’s not the “new norm” unless employees accept it as the new normal. I don’t know why anyone would accept a completely one-sided situation like that.
> I need to be able to support what I ship and answer to the details of what it does and why it does it. I can only truly do that if I write it myself.
How do you function on a team, where you have to maintain code others have written?
We talk to each other. If someone wrote something I don't understand, I defer to them. If someone wrote something who is no longer with the company, we trying to make sense of it, and in some cases end up re-writing some things.
There are only 3 or 4 of us working on most of the code I touch. 3 of us have worked together in some form or another for close to 20 years.
This past week I found and fixed a bug that happens once in 40,000 transactions working with Claude Code - Opus 4.6. Our legacy app was designed around 2008 and has had zillions of band aids added since then. Nobody (~700 person company) has been able to reliably reproduce this issue to confidently claim that they know what the cause is and how to definitively fix it. That all changed yesterday. I spent today writing up summaries that were shared far and wide. My wizard status is yet again renewed.
I'm over 50 now and feel like this as well. Haven't used Claude yet but used Codex a bunch, and it's been SO MUCH fun going over all the old perl & shell scripting stuff that I used to do years ago before I got into healthcare time and morphed to a hobby sysadmin.
Staying up and re-learning what I used to love long ago has given me a new found passion as well. Even if I do vibe code some scripts, at least I have the background now to go through them and make sure they make sense. They're things I'm using in my own homelab and not something that I'm trying to spin up a Github repo for. I'm not shipping anything. I'm refreshing my old skills and trying to bring some of them up to date.
An unfortunate reality is that my healthcare career is going to be limited due to multiple injuries along the way, and I need to try to be as current as I can in case something happens. My safety net is limited.
So excited to be getting to my backlog of apps that I've wanted but couldn't take the time to develop on my own. I'm 66 and have been in the software field in various capacities (but programming mostly as a hobby). Here's a partial list of apps I've completed in the last few months:
- Media Watch app to keep a list of movies and shows my wife and I want to watch
- Grocery List with some tracking of frequent purchases
- Health Log for medical history, doc appointments and past visits
- Habits Tracker with trends I’m interested
- Daily Wisdom Reader instead of having multiple ebooks to keep track of where I'm at
- A task manager similar to the old LifeBalance app
- A Home Inventory app so that I can track what I have, warranty, and maintenance
- An ios watch app to see when I'm asleep so that it can turn off my music or audiobook
- An ios watch chess tactics trainer app
- some games
Many of these are similar to paid offerings, but those didn't check off all the features I really wanted, so I vibe-coded my own. They all do what I want, the way I want it to.
This is the reason. I have just been vibe-coding my way for a few months now, got almost all the tools (except Browser and Mail) that I use daily, designed by me (with the help of LLM).
Maybe the internet has made me too cynical, and I'm glad people seem to be having a good time, but at time of posting I can't help but notice that almost every comment here is suspiciously vague as to what, exactly, is being coded. Still better than the breathless announcements of the death of software engineering, but quite similar in tone.
The other week I used Copilot to write a program that scans all our Amazon accounts and regions, collects services and versions, and finds the ones going EOL within a year. The data on EOL dates is scraped from several sources and kept in JSON. There's about 16 different AWS API calls used. It generates reports in markdown, json, and csv, so humans can read the markdown (flags major things, explains stuff), and the csv can be used to triage, prioritize, track work over time. The result is deduplicated, sorted, consolidated (similar entries), and classified. I can automatically send reports to teams based on a regex of names or tags. This is more data than I get from AWS Health Dashboard, and can put it into any format I want, across any number of accounts/regions.
Afaik there are no open source projects that do this. AWS has a behemoth of a distributed system you can deploy in order to do something similar. But I made a Python script that does it in an afternoon with a couple of prompts.
I am currently using a Claude skill that I have been building out over the last few days that runs through my Amazon PPC campaigns and does a full audit. Suggestions of bid adjustments, new search terms and products to advertise against and adjustment to campaign structures. It goes through all of the analytics Amazon provides, which are surprisingly extensive, to find every search term where my product shows up, gets added to cart and purchased.
It's the kind of thing that would be hours of tedious work, then even more time to actually make all the changes to the account. Instead I just say "yeah do all of that" and it is done. Magic stuff. Thousands of lines of Python to hit the Amazon APIs that I've never even looked at.
It's thousands of lines of variation on my own hand-tooling, run through tests I designed, automated by the sort of onboarding docs I should have been writing years ago.
Do you trust the assembly your compiler puts out? The machine code your assembler puts out? The virtual machine it runs on? Thousands of lines of code you've never looked at...
We agree then that you can verify, test, and trust the deterministic code an LLM produces without ever looking at it.
> That's one reason we test
That's one way we can trust and verify code produced by an LLM. You can't stop doing all the other things that aren't coding.
I get there's a difference. Shitty code can be produced by LLMs or humans. LLMs really can pump out the shitty code. I just think the argument that you cant trust code you haven't viewed is not a good argument. I very much trust a lot of code I've never seen, and yes I've been bitten by it too.
Not trying to be an ass, more trying to figure out how im going to deal for the next decade before retirement age. Uts going to be a lot of testing and verification I guess
- A slimmed-down phpBB 2 "remake" in Bun.js/TypeScript
- An experimental SQLite extension for defining incremental materialized views
...And many more that are either too tiny, too idiosyncratic, or too day-job to name here. Some of these are one-off utilities, some are toys I'll never touch again, some are part of much bigger projects that I've been struggling to get any work done on, and so on.
I don't blame you for your cynicism, and I'm not blind to all of the criticism of LLMs and LLM code. I've had many times where I feel upset, skeptical, discouraged, and alienated because of these new developments. But also... it's a lot of fun and I can't stop coming up with ideas.
Yes! Although 60 is still a decade away, I've spent a fair few evenings vibe-coding a FOSS dependency-free raw git repo browser.[1] Never would have even started such a project without LLMs because:
* Implementing a raw Git reader is daunting.
* Codifying syntax highlighting rules is laborious.
* Developing a nice UI/UX is not super enjoyable for me.
* Hardening with latest security measures would be tricky.
* Crafting a templating language is time-consuming.
Being able to orchestrate and design the high-level architecture while letting the LLM take care of the details is extremely rewarding. Moving all my repositories away from GitLab, GitHub, and BitBucket to a single repo under my own control is priceless.
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!
I remember before style sheets existed. Webites were all nested tables and font tags. I built a video website before YouTube be even existed. Claude code and AI is definitely an exciting time.
I'm 38 years old, and as a manager, it's gradually become difficult to find joy in coding. Claude Code has helped me rediscover that pleasure. Now, all I want to do is code every day and use up my quota.
I’m a 13 year lurker, first time commenter (Not sure why this post compelled me). I don’t think this is a genuine take. I don’t see how a 60 year old has any kind of joy for actual software creation suddenly from llms. It might be a joy in seeing software automatically be created but it’s definitely not doing the work. (I may be biased, I left the field 5 years ago) I doubt he’s spending any time fixing the software to make it near usable for anyone besides himself and the semi-working state the llm gave him. Meaning he’s going to have 10 or more half-finished projects again.
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
Just checked out MoveOMeter.com Great idea - and I get how pitching to "an old coot" like my parents would get a laugh out of them before an insulting hurtful pass. Very clever positioning - I'd lean in on that. Your audience is there and waiting - which is tricky since your customer is actually the sales person and you need to give them the training up front to close the deal with their elder. Nice work!
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.
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.
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!
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.
The English language has the ability to be ambiguous, but I bet AI use will change the way we use the English language colloquially, to say more specifically what we mean. I worked as a home inspector for a while. Writing for an LLM is very similar to writing a home inspection report or legal brief (or talking to a group of teenagers). Navigate the minefield with very specific intention.
Same, early 50s and this is like the heyday of coding where you could rapidly iterate on things and actively make leaps and bounds of progress. Super fun.
I'll be 38 next month. I always wonder what I'm do in 30 more years and I cannot see myself NOT coding. Happy to see that spark is alive and well within you.
I see many comments here about Claude and I get the same feeling I get when I see comments about MacOS: it's nice that you're content with it, but I don't trust Apple/Anthropic for a fraction of an angstrom.
Wake me when we have ethically trained, open source models that run locally. Preferably high-quality ones.
btw how good are any of these tools for embedded programming? we need a new era for hardware enthusiasts. my dad made plenty of fun things in the 80s but it was at the tail end of the newess that came from radiokits and other gadgets that flooded the market due to the uchip
all the insane and/or speculative projects that i never did because they would require heavy lift but with vague outcomes are now in progress. it's glorious.
I'm so excited to be able to continue build things when I'm living on the streets. I'm glad to know that drive to create will always be with me and keep me warm during winters.
You can't speak this kind of truth on hacker news!
But, uh, yeah... I've been noticing a growing divide between people like OP who are either already retired or are wealthy enough that they could if they wanted to who absolutely love the new world of LLMs, and people who aren't currently financially secure and realize that LLMs are going to snatch their career away. Maybe not this year, but not too far out either.
What I think is lost on ones like OP, is that yes, they are financially secure in the current climate. But if the future that everyone seems to be ushering in does come true, even ones like OP will be in a different state of security.
How does the saying go again? "It takes a village to reach financially secure retirement"
I’m on a field trip chaperoning my kid. I get a couple slack messages asking for some tweaks to a UI. I type a couple words into a Github AI Agent Session while riding the bus. Fixes are deployed to our staging env in 10 minutes.
try asking claude to write in VB6. Make some Active Server Pages. Use COM components. Why not? We can do things "better" now, but what does that matter when you can do the same things as before, but better?
I have bipolar disorder. The more frustrating aspects of coding have historically affected me tenfold (sometimes to the point of severe mania). Using Claude Code has been more like an accessibility tool in that regard. I no longer have to do the frustrating bits. Or at the very least, that aspect of the job is thoroughly diminished. And yes - coding is "fun again".
I think coding can be an endurance sport sometimes. There are a lot of points at which you have to bang your head against a wall for hours or days to figure out the smallest issue. Having an agent do that frustrating part definitely lowers the endurance needed to stay productive on a project.
I have this idea that probably violates some law of computing but I am really stubborn to make it happen somehow.
I want a game that generates its own mechanics on the fly using AI. Generates itself live.
Infinite game with infinite content. Not like no mans sky where everything is painfully predictable and schematic to a fault. No. Something that generates a whole method of generating. Some kind of ultra flexible communication protocol between engine and AI generator that is trained to program that protocol.
Develop it into a framework.
Use that framework to create one game. A dwarf fortress adventure mode 2.0
I have no other desires, I have no other goals, I don’t care. I or better yet - someone else, must do it.
Claude Code and it's parallels have extinguished multiple ones.
I was able to steer clear of the Bitcoin/NFT/Passport bros but it turns out they infiltrated the profession and their starry puppy delusional eyes are trying to tell me that iteration X of product Y released yesterday evening is "going to change everything".
They have started redefining what "I have build this" actually means, and they have outjerked the executives by slinging outrageous value creation narratives.
> I’m chasing the midnight hour and not getting any sleep.
You are 60; go spend some time with your grand-kids, smell a flower, touch grass forget chasing anything at this age cause a Tuesday like the others things are gonna wrap up.
My main worry is: what is the license on the code produced by Claude (or any other coding agent)? It seems like, if it was trained using open-source software, then the resulting code needs to be open-source as well and it should be compatible with the original source. Artwork produced by an AI cannot be copyrighted, but apparently code can be?
If the software produced is for internal use, the point is probably moot. But if it isn't, this seems like a question that needs to be answered ASAP.
Hey, I'm nearly 80 years old. I haven't written a line of code in over 10 years. But I'm coding now, with the help of Claude & Gemini, and having a great time. Each block of Python or Applescript that they generate for me is a much better learning tool than a book - I'm going through the code line by line and researching everything. And I'm also learning how to deal with LLMs and their strengths & weaknesses. Correcting them from time to time when they screw up. Lots of fun.
It's cool to rediscover Applescript for me (I'm late 40's) but it's a funny thing where I can like smell the NeXT in it almost nostalgically but it's quite handy in this new era of hijacking mac mini's (OpenClaw obviously is one way to do it, but why not just straight to the core).
I personally think coders get better with age, like lounge singers.
AppleScript doesn’t have any NeXT heritage, it comes entirely from classic MacOS (debuted in System 7.1)
I'm very happy for you and hope when I'm nearing 80 I get to be doing something similar.
Same here - it's like programming with a couple of buddies. Occasionally they goof off and wreck everything, but we put it back together and end up with a finished project. I'm literally going through my backlog of projects from the early 80s! There are parts of each of these projects that were black holes for me - just didn't know enough to get a toe hold. With Karl (that's my agent) he explains everything I don't understand, does stuff, breaks stuff, and so on. It's really a blast.
> it's like programming with a couple of buddies. Occasionally they goof off and wreck everything,
Nailed it :)
This comment about the OpenClaw guy hits a little too close to home:
“Peter Steinberger is a great example of how AI is catnip very specifically for middle-aged tech guys. they spend their 20s and 30s writing code, burn out or do management stuff for a decade, then come back in their late 40s/50s and want to try to throw that fastball again. Claude Code makes them feel like they still got it.”
Same but for me it's 25 years of accumulated personal backlog that I'm finally burning through. Like I've been a project hoarder and now I have a house elf to tidy up and do all that widget fobbering business. I just need to figure out what the rules of the house are.
And why would they not? do they have to feel they ain’t got it anymore because age?
> late 40s
This describes me nearly perfectly. Though I didn’t exactly burn out of coding, I accidentally stumbled upon being an EM while I was coding well and enjoying. But being EM stuck so I got into managing team(s) at biggish companies which means doing everything except one that I enjoy the most which is coding.
However now that I run my own startup I’m back to enjoying coding immensely because Claude takes care of grunt work of writing code while allowing me to focus on architecture, orchestration etc. Immense fun.
If you don’t mind sharing, what does your startup do?
As a principal engineer I feel completely let down. I've spent decades building up and accumulating expert knowledge and now that has been massively devalued. Any idiot can now prompt their way to the same software. I feel depressed and very unmotivated and expect to retire soon. Talk about a rug pull!
My experience is that people who weren't very good at writing software are the ones now "most excited" to "create" with a LLM.
Same here, although hopefully won't be retiring soon.
What's missing from this is that iconic phrase that all the AI fans love to use: "I'm just having fun!"
This AI craze reminds me of a friend. He was always artistic but because of the way life goes he never really had opportunity to actively pursue art and drawing skills. When AI first came out, and specifically MidJourney he was super excited about it, used it a lot to make tons and tons of pictures for everything that his mind could think of. However, after awhile this excitement waned and he realized that he didn't actually learn anything at all. At that point he decided to find some time and spend more time practicing drawing to be able to make things by himself with his own skills, not by some chip on the other side of the world and he greatly improved in the past couple of years.
So, AI can certainly help create all the "fun!!!" projects for people who just want to see the end result, but in the end would they actually learn anything?
> My experience is that people who weren't very good at writing software are the ones now "most excited" to "create" with a LLM.
I've been a tech lead for years and have written business critical code many times. I don't ever want to go back to writing code. I am feeling supremely empowered to go 100x faster. My contribution is still judgement, taste, architecture, etc. And the models will keep getting better. And as a result, I'll want to (and be able to) do even more.
I also absolutely LOVE that non-programmers have access to this stuff now too. I am always in favor of tools that democratize abilities.
Any "idiot" can build their own software tailored to how their brains think, without having to assemble gobs of money to hire expensive software people. Most of them were never going to hire a programmer anyway. Those ideas would've died in their heads.
What you bring to the table night be fine, but how long do you think you'll find emoloyers willing to still pay for this?
One thing is for sure LLMs will bring down down the cost of software per some unit and increase the volume.
But..cost = revenue. What is a cost to one party is a revenue to another party. The revenue is what pays salaries.
So when software costs go down the revenues will go down too. When revenues go down lay offs will happen, salary cuts will happen.
This is not fictional. Markets already reacted to this and many software service companies took a hit.
I consider myself very good at writing software. I built and shipped many projects. I built systems from zero. Embedded, distributed, SaaS- you name it.
I'm having a lot of fun with AI. Any idiot can't prompt their way to the same software I can write. Not yet anyways.
I’m with you here.
I grew up without a mentor and my understanding of software stalled at certain points. When I couldn’t get a particular os API to work, in Google and stack overflow didn’t exist, and I had no one around me to ask. I wrote programs for years by just working around it.
After decades writing software I have done my best to be a mentor to those new to the field. My specialty is the ability to help people understand the technology they’re using, I’ve helped juniors understand and fix linker errors, engineers understand ARP poisoning, high school kids debug their robots. I’ve really enjoyed giving back.
But today, pretty much anyone except for a middle schooler could type their problems into a ChatGPT and get a more direct answer that I would be able to give. No one particularly needs mentorship as long as they know how to use an LLM correctly.
Today every single software engineer has an extremely smart and experienced mentor available to them 24/7. They don't have to meet them for coffee once a month to ask basic questions.
That said, I still feel strongly about mentorship though. It's just that you can spend your quality time with the busy person on higher-level things, like relationship building, rather than more basic questions.
As a Principal SWE, who has done his fair share of big stuff.
I'm excited to work with AI. Why? Because it magnifies the thing I do well: Make technical decisions. Coding is ONE place I do that, but architecture, debugging etc. All use that same skill. Making good technical decisions.
And if you can make good choices, AI is a MEGA force multiplier. You just have to be willing to let go of the reins a hair.
> As a principal engineer I feel completely let down. I've spent decades building up and accumulating expert knowledge and now that has been massively devalued. Any idiot can now prompt their way to the same software. I feel depressed and very unmotivated and expect to retire soon. Talk about a rug pull!
Really?
The vibe coders are running into a dark forest with a bunch of lobsters (OpenClaw) getting lost and confused in their own tech debt and you're saying they can prompt their way to the same software?
Someone just ended up wiping their entire production database with Claude and you believe that your experience is for nothing, towards companies that need stable infrastructure and predictability.
Cognitive debt is a real thing and being unable to read / write code that is broken is going to be an increasing problem which experienced engineers can solve.
Do not fall for the AI agent hype.
What I keep hearing is that the people who weren't very good at writing software are the ones reluctant to embrace LLMs because they are too emotionally attached to "coding" as a discipline rather than design and architecture, which are where the interesting and actually difficult work is done.
IMHO any idiot can create a piece of crap. It takes experience to create good software. Use your experience Luke! Now you have a team of programmers to create what ever you fancy! Its been great for me, but I have only been programming C++ for 36 years.
No offense but you sound more like a “principle coder”, not a principle engineer. At least in many domains and orgs, Most principal engineers are already spending most their time not coding. But -engineering- still take sip much or most of their time.
I felt what you describe feeling. But it lasted like a week in December. Otherwise there’s still tons of stuff to build and my teams need me to design the systems and review their designs. And their prompt machine is not replacing my good sense. There’s plenty of engineering to do, even if the coding writes itself.
On the bright side, working in tech between 2006 and 2026 means you should be extremely wealthy and able to retire comfortably.
I spent the last 2 days primarily using Claude instead of coding things myself at work. I felt the exact opposite way. It was so unfulfilling. I’d equate it to the feeling of getting an A on a test, knowing I cheated. I didn’t accomplish anything. I didn’t learn anything. I got the end result with none of the satisfaction and learned nothing in the process.
I’m probably going to go back and redo everything with my own code.
That's interesting. I have been thinking about how the vastly different reactions people seem to have to agentic coding could be influenced by what they value about coding. To me it seems like there are three joys in coding:
1. Creating something
2. Solving puzzles
3. Learning new things
If you are primarily motivated by seeing a finished product of some sort, then I think agentic coding is transcendent. You can get an output so much quicker.
If your enjoyment comes from solving hard puzzles, digging into algorithms, how hardware works, weird machine quirks, language internals etc... then you're going to lose nearly all of that fun.
And learning new things is somewhere in the middle. I do think that you can use agentic coding to learn new technologies. I have found llms to be a phenomenal tool for teaching me things, exploring new concepts, and showing me where to go to read more from human authors. But I have to concede that the best way to learn is by doing so you will probably lose out on some depth and stickiness if you're not the one implementing something in a new technology.
Of course most people find joy in some mix of all three. And exactly what they're looking for might change from project to project. I'm curious if you were leaning more towards 2 and 3 in your recent project and that's why you were so unsatisfied with Claude Code.
I'll add "craftsmanship". It isn't just delivering "A" finished product, you want to deliver a "good", if not "the best", finished product.
I guess if you're in an iterative MVP mindset then this matters less, but that model has always made me a little queasy. I like testing and verifying the crap out of my stuff so that when I hand it off I know it's the best effort I could possibly give.
Relying on AI code denies me the deep knowledge I need to feel that level of pride and confidence. And if I'm going to take the time to read, test and verify the AI code to that level, then I might as well write most of it unless it's really repetitive.
I don't think AI coding means you stop being a craftsman. It is just a different tool. Manual coding is a hand tool, AI coding is a power tool. You still retain all of the knowledge and as much control over the codebase as you want, same with any tool.
It's a different conversation when we talk about people learning to code now though. I'd probably not recommend going for the power tool until you have a solid understanding of the manual tools.
That's a really good point. And I agree that kind of confidence in craftsmanship is something that's missing from agentic coding today... it does make slop if you're not careful with it. Even though I've learned how to guide agents, I still have some uneasiness about missing something sloppy they have done.
But then it makes me ask if the agents will get so good that craftsmanship is a given? Then that concern goes away. When I use Go I don't worry too much about craftsmanship of the language because it was written by a lot of smart people and has proven itself to be good in production for thousands of orgs. Is there a point at which agents prove themselves capable enough that we start trusting in their craftsmanship? There's a long way to go, but I don't think that's impossible.
I'm squarely into #1, but it usually requires #2 (at a high level) and has #3 as a side effect. But there's also #0 which kicks it all off: the triggering problem/question.
Like just yesterday I started to notice the increasing pressure of an increasingly hard-to-navigate number of Claude chats. So I went searching for something to organize them. I did find an extension, but it's for Chrome, and I'm a Firefox person, so I had Claude look at it with the initial idea of porting to Firefox. Then in the analysis, Claude mentioned creating an extension from scratch, and that's what I went for.
I've never really used JavaScript, let alone created a Firefox extension before, but in a few minutes I was iterating on one, figuring out how I wanted it to work with Claude, and now I have a very nice and featureful chats organizer. And I haven't even peeked at the code. I also now have a firm idea of this general spec of how I want arbitrary list-organizing UI to look+behave going forward.
I can see where this idea is coming from, but I don't agree with the conclusion at all. As someone who loves solving puzzles and learning new things, AI has been a godsend. I also very much like creating things, but even more than that, I like doing all three at once.
I think of AI like a microdose of Speed Force. Having super speed doesn't mean you don't like running; it just means you can run further and more often. That in turn justifies a greater amount of time spent running.
Without the Speed Force, most of the time you were reliant on vehicles (i.e. paying for third-party solutions) to get where you needed to go. With the Speed Force, not only can you suddenly meet a lot more of your transportation needs by foot, you're able to run to entirely new destinations that you'd never before considered. Eventually, you may find yourself planning trips to yet unexplored faraway harsh terrains.
If your joy in running came from attempting to push your biological physical limits, maybe you hate the Speed Force. If you enjoy spending time running and navigating unfamiliar territory, the Speed Force can give you more of that.
Sure, there are also oddballs who don't know how to run, yet insist on using the Speed Force to awkwardly jump somewhere vaguely in the vicinity of their destination. No one's saying they don't exist, but that's a completely different crowd from experienced speedsters.
> If you are primarily motivated by seeing a finished product of some sort, then I think agentic coding is transcendent
As someone who enjoys technology, and using it, and can just barely sort-of code but really not, agentic coding must be wonderful. I have barely scratched the surface with a couple of scripts. But simply translating "here's what I want, and how I would have done it the last time I used Linux 20 years ago, show me how to do it with systemd" is so much easier than digging through years of forum posts and trying to make sure they haven't all been obsoleted.
None of it is new. None of it is fancy. I do regret that people aren't getting credit for their work, but "automount this SMB share from my NAS" isn't going to make anyone's reputation. It's just going to make my day easier. I really did learn enough to set up a NAT system to share a DSL connection with an office in the late 1990s on OpenBSD. It took a long time, and I don't have that kind of free time anymore. I will never git gud. It's this, or just be another luser who goes without.
I think I'd add a #4 to this list, and that's helping people. I like making things that people can use to make their life easier. That's probably my number one.
The "creating something" idea... That's more complex. With agentic coding something can be created, but did I create it? Using agentic coding feels like hiring someone to do the work for me. For example, I just had all the windows in my house replaced. A crew came out at did it. The job is done, but I didn't do anything and felt no pride or sense of accomplishment in having these new windows. It just happened. Contrast that to a slow drain I had in my bathroom. I took the pipes apart, found the blockage, cleared it out, and reassembled the drain. When I next used the sink and the water effortlessly flowed away, I felt like I accomplished something, because I did it, not some plumber I hired.
So it isn't even about learning or solving puzzles, it's about being the person who actually did the work and seeing the result of that effort.
Yes! Good points! I think what I meant for point 1 was more "outputting something" vs "creating something". In my mind that encompasses materializing something into the world to achieve whatever you wanted, whether you were aiming to help others, solve a problem you alone have, or scratch some other sort of itch. It's about achieving some end. And helping somebody can be achieved indirectly and still be satisfying.
The inherent value of creating is something I was missing. Solving puzzles might be part of that, but not all. It's the classic Platonic question about how we value actions: for their own sake, for their results, or for both.
I think we agree that coding can be both, and it sounds like you feel the value for its own sake is lackluster in agentic coding -- It's just too easy. And I think that's the core sliding scale: Do you value creation more for its own sake or for its results? Where you land on that spectrum probably influences how people feel about agentic coding.
That being said, I also think that agentic coding can give enough of a challenge to scratch the itch of intrinsic value of creating. To a certain degree I think it's about moving up the abstraction chain to work more on architecture and product design. Those things can be fun and rewarding too. But fundamentally it's a preference.
It's kind of a weird thing. I spent 2 days working one some code, which in a way was the process of working out the requirements and functionality that was required. I then told Claude to look at it in and refactor it.
I did put in 2 days of work to come up with what Claude used to ultimately do what it did... but when I look at the resulting code, I feel nothing. Having the idea isn't the same as being the one who actually did the thing. I plan to delete the branch next week. I don't want to maintain what it did, and think it should be less complex than it made it.
You're forgetting that (1) brings a sense of pride. "I built this". That's not true in many ways if you ask something else to do it
I think your comment really captures some of the reasons behind the differences between people’s reactions to Claude pretty well.
I will add though, on 2 and 3, during most of the coding I do in my day job as a staff engineer, it’s pretty rare for me to encounter deeply interesting puzzles and really interesting things to learn. It’s not like I’m writing a compiler or and OS kernel or something; this is web dev and infra at a mid sized company. For 95% of coding tasks I do I’ve seen some variation already before and they are boring. It’s nice to have Claude power through them.
On system design and architecture, the problems still tend to be a bit more novel. I still learn things there. Claude is helpful, but not as helpful as it is for the code.
I do get the sense that some folks enjoy solving variations of familiar programming puzzles over and over again, and Claude kills that for them. That’s not me at all. I like novelty and I hate solving the same thing twice. Different tastes, I guess.
When it comes to writing code, I can almost tell before writing code that whether this particular piece of code will be intellectually stimulating to me. If so, I write it myself without thinking about whether Claude might have done it faster. If not, I let Claude write it. Currently I'd estimate maybe 70% of the code falls in the first category, and the remaining 30% is something I would've used a lot of my own willpower to get started anyways.
Also, when I write code myself, I still ask Claude to review it. It's faster than asking a human colleague to review it, so you can have Claude review often. Just today after a five-minute review Claude said a piece of code I wrote had four bugs, three of which were hallucinations and one was a real bug. I honestly do think it would have taken me a bit more than five minutes to find that one real bug.
The creator of OpenClaw had a great line about this:
"If your identity is tied to you being an iOS developer, you are going to have a rough time. But if your identity is 'I'm a builder!' it is a very exciting time to be alive."
Plus, there is no rule that says you can't keep coding if it's faster for you and/or it's quicker in general. e.g I can write a Perl one liner much faster than Claude can. Heck, even if it's not faster and you enjoy coding, just keep coding.
I'm a few years younger than the OP, but I remember the early Internet days. I started with Perl CGI scripts, ASP, even some early server side JS, in the form of Netscape Livewire.
Over the past couple months, I've created several applications with Claude Code. Personal projects that would've taken me weeks, months, or possibly forever, since I generally get distracted and move on to something else. I write pretty decent specs, break things into phases, and make sure each phase is solid before moving on to the next.
I have Claude build things in frameworks I would've never tried myself, just because it can. I do actually look at the code. Some of it is slop. In a few cases, it looks like it works, but it'll be a totally naive or insecure implementation. If I really don't like how it did something, I'll revert and give it another attempt. I also have other AIs review it and make suggestions.
It's fun, but I ultimately gain little intellectual satisfaction from it. It's not like the old days at all. I don't feel like I'm growing my skill set. Yes, I learned "something", but it's more about the capabilities of AI, not the end result.
Still, I'm convinced this is the future. Experienced developers are in the best position to work with AI. We also may not have a choice.
You're paid by a company to create software, so they can use it to drive business value and make a profit. You did so effortlessly. But it didn't make you feel personally fulfilled. So you're going to go back and re-do it, so you feel better?
How do you think your company's CEO is going to feel when you tell them you could be finishing the software much faster, but you'd rather not, because it feels better to do it by hand?
For fun and education purposes, learning and satisfaction are understandable.
For work, companies won't support it. Get it done. Fast. That's the new norm.
I disagree. I need to be able to support what I ship and answer to the details of what it does and why it does it. I can only truly do that if I write it myself.
There should also be a symbiotic relationship at a job. Yes, they get something from me, but I should also get something… learning and some amount of satisfaction… in addition to the paycheck. I can get a paycheck anywhere.
It’s not the “new norm” unless employees accept it as the new normal. I don’t know why anyone would accept a completely one-sided situation like that.
> I need to be able to support what I ship and answer to the details of what it does and why it does it. I can only truly do that if I write it myself.
How do you function on a team, where you have to maintain code others have written?
We talk to each other. If someone wrote something I don't understand, I defer to them. If someone wrote something who is no longer with the company, we trying to make sense of it, and in some cases end up re-writing some things.
There are only 3 or 4 of us working on most of the code I touch. 3 of us have worked together in some form or another for close to 20 years.
This past week I found and fixed a bug that happens once in 40,000 transactions working with Claude Code - Opus 4.6. Our legacy app was designed around 2008 and has had zillions of band aids added since then. Nobody (~700 person company) has been able to reliably reproduce this issue to confidently claim that they know what the cause is and how to definitively fix it. That all changed yesterday. I spent today writing up summaries that were shared far and wide. My wizard status is yet again renewed.
Your choices are not limited to one extreme or the other.
I think it depends what you're building. I find it fun, once in a while, an engineer to "not go shoeless" and get some of things I need done.
I'm over 50 now and feel like this as well. Haven't used Claude yet but used Codex a bunch, and it's been SO MUCH fun going over all the old perl & shell scripting stuff that I used to do years ago before I got into healthcare time and morphed to a hobby sysadmin.
Staying up and re-learning what I used to love long ago has given me a new found passion as well. Even if I do vibe code some scripts, at least I have the background now to go through them and make sure they make sense. They're things I'm using in my own homelab and not something that I'm trying to spin up a Github repo for. I'm not shipping anything. I'm refreshing my old skills and trying to bring some of them up to date. An unfortunate reality is that my healthcare career is going to be limited due to multiple injuries along the way, and I need to try to be as current as I can in case something happens. My safety net is limited.
- Grocery List with some tracking of frequent purchases
- Health Log for medical history, doc appointments and past visits
- Habits Tracker with trends I’m interested
- Daily Wisdom Reader instead of having multiple ebooks to keep track of where I'm at
- A task manager similar to the old LifeBalance app
- A Home Inventory app so that I can track what I have, warranty, and maintenance
- An ios watch app to see when I'm asleep so that it can turn off my music or audiobook
- An ios watch chess tactics trainer app
- some games
Many of these are similar to paid offerings, but those didn't check off all the features I really wanted, so I vibe-coded my own. They all do what I want, the way I want it to.
This is the reason. I have just been vibe-coding my way for a few months now, got almost all the tools (except Browser and Mail) that I use daily, designed by me (with the help of LLM).
And the biggest thing is that: software the way we want is much easier. No ads. No monthly cost.
Maybe the internet has made me too cynical, and I'm glad people seem to be having a good time, but at time of posting I can't help but notice that almost every comment here is suspiciously vague as to what, exactly, is being coded. Still better than the breathless announcements of the death of software engineering, but quite similar in tone.
The other week I used Copilot to write a program that scans all our Amazon accounts and regions, collects services and versions, and finds the ones going EOL within a year. The data on EOL dates is scraped from several sources and kept in JSON. There's about 16 different AWS API calls used. It generates reports in markdown, json, and csv, so humans can read the markdown (flags major things, explains stuff), and the csv can be used to triage, prioritize, track work over time. The result is deduplicated, sorted, consolidated (similar entries), and classified. I can automatically send reports to teams based on a regex of names or tags. This is more data than I get from AWS Health Dashboard, and can put it into any format I want, across any number of accounts/regions.
Afaik there are no open source projects that do this. AWS has a behemoth of a distributed system you can deploy in order to do something similar. But I made a Python script that does it in an afternoon with a couple of prompts.
I am currently using a Claude skill that I have been building out over the last few days that runs through my Amazon PPC campaigns and does a full audit. Suggestions of bid adjustments, new search terms and products to advertise against and adjustment to campaign structures. It goes through all of the analytics Amazon provides, which are surprisingly extensive, to find every search term where my product shows up, gets added to cart and purchased.
It's the kind of thing that would be hours of tedious work, then even more time to actually make all the changes to the account. Instead I just say "yeah do all of that" and it is done. Magic stuff. Thousands of lines of Python to hit the Amazon APIs that I've never even looked at.
And it doesn't freak you out that you're relying on thousands of lines of code that you've never looked at? How do you verify the end result?
I wouldn't trust thousands of lines of code from one of my co-workers without testing
It's thousands of lines of variation on my own hand-tooling, run through tests I designed, automated by the sort of onboarding docs I should have been writing years ago.
Do you trust the assembly your compiler puts out? The machine code your assembler puts out? The virtual machine it runs on? Thousands of lines of code you've never looked at...
None of that is generated by an LLM prone to hallucination and is perfectly deterministic unless there's a hardware problem.
And yes, I have occasionally run into compiler bugs in my career. That's one reason we test.
> None of that is generated by an LLM
How did you verify that?
> prone to hallucination
You know humans can hallucinate?
> is perfectly deterministic
We agree then that you can verify, test, and trust the deterministic code an LLM produces without ever looking at it.
> That's one reason we test
That's one way we can trust and verify code produced by an LLM. You can't stop doing all the other things that aren't coding.
I get there's a difference. Shitty code can be produced by LLMs or humans. LLMs really can pump out the shitty code. I just think the argument that you cant trust code you haven't viewed is not a good argument. I very much trust a lot of code I've never seen, and yes I've been bitten by it too.
Not trying to be an ass, more trying to figure out how im going to deal for the next decade before retirement age. Uts going to be a lot of testing and verification I guess
"Trust"? God no. That's why I have a debugger
In the past month, in my spare time, I've built:
- A "semantically enhanced" epub-to-markdown converter
- A web-based Markdown reader with integrated LLM reading guide generation (https://i.imgur.com/ledMTXw.png)
- A Zotero plugin for defining/clarifying selected words/sentences in context
- An epub-to-audiobook generator using Pocket TTS
- A Diddy Kong Racing model/texture extractor/viewer (https://i.imgur.com/jiTK8kI.png)
- A slimmed-down phpBB 2 "remake" in Bun.js/TypeScript
- An experimental SQLite extension for defining incremental materialized views
...And many more that are either too tiny, too idiosyncratic, or too day-job to name here. Some of these are one-off utilities, some are toys I'll never touch again, some are part of much bigger projects that I've been struggling to get any work done on, and so on.
I don't blame you for your cynicism, and I'm not blind to all of the criticism of LLMs and LLM code. I've had many times where I feel upset, skeptical, discouraged, and alienated because of these new developments. But also... it's a lot of fun and I can't stop coming up with ideas.
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...
Yes! Although 60 is still a decade away, I've spent a fair few evenings vibe-coding a FOSS dependency-free raw git repo browser.[1] Never would have even started such a project without LLMs because:
* Implementing a raw Git reader is daunting.
* Codifying syntax highlighting rules is laborious.
* Developing a nice UI/UX is not super enjoyable for me.
* Hardening with latest security measures would be tricky.
* Crafting a templating language is time-consuming.
Being able to orchestrate and design the high-level architecture while letting the LLM take care of the details is extremely rewarding. Moving all my repositories away from GitLab, GitHub, and BitBucket to a single repo under my own control is priceless.
[1]: https://repo.autonoma.ca/treetrek/
A great thing you can do with LLMs:
"in (language I'm familiar with) I use (some pattern or whatever) what's the equivalent in (other language)?"
It's really great for doing bits and then get it to explain or you look and see what's wrong and modify it and learn.
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!
I remember before style sheets existed. Webites were all nested tables and font tags. I built a video website before YouTube be even existed. Claude code and AI is definitely an exciting time.
And transparent 1 pixel gifs :-)
don't forget VRML there are dozens of us
I'm 38 years old, and as a manager, it's gradually become difficult to find joy in coding. Claude Code has helped me rediscover that pleasure. Now, all I want to do is code every day and use up my quota.
I’m a 13 year lurker, first time commenter (Not sure why this post compelled me). I don’t think this is a genuine take. I don’t see how a 60 year old has any kind of joy for actual software creation suddenly from llms. It might be a joy in seeing software automatically be created but it’s definitely not doing the work. (I may be biased, I left the field 5 years ago) I doubt he’s spending any time fixing the software to make it near usable for anyone besides himself and the semi-working state the llm gave him. Meaning he’s going to have 10 or more half-finished projects again.
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
51 year old electrical engineer here, same thing! (minus the retiring part cause finances)
It's given me the guts to be a solo-founder (for now). I
Just checked out MoveOMeter.com Great idea - and I get how pitching to "an old coot" like my parents would get a laugh out of them before an insulting hurtful pass. Very clever positioning - I'd lean in on that. Your audience is there and waiting - which is tricky since your customer is actually the sales person and you need to give them the training up front to close the deal with their elder. Nice work!
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.
Everything in this post is proof that Anthropic will kill it when they go public. I believe in it, so does everyone else.
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.
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!
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.
I’ve been trying to learn a lot about domain driven design, I think knowledge crunching will be a huge part of the new software development role.
Was chatting with a friend about this:
"I used to write java code and the compiler turned it into JVM bytecode.
Now I write in English and the LLMs compile it into whatever language I want."
Although as one HN commenter pointed out: English is a pretty bad programming language as it's way more ambiguous than most programming languages.
The English language has the ability to be ambiguous, but I bet AI use will change the way we use the English language colloquially, to say more specifically what we mean. I worked as a home inspector for a while. Writing for an LLM is very similar to writing a home inspection report or legal brief (or talking to a group of teenagers). Navigate the minefield with very specific intention.
Same, early 50s and this is like the heyday of coding where you could rapidly iterate on things and actively make leaps and bounds of progress. Super fun.
I'll be 38 next month. I always wonder what I'm do in 30 more years and I cannot see myself NOT coding. Happy to see that spark is alive and well within you.
It's taken over my life, I am in a leadership position at faang but i'm daydreaming about getting back to my claude sessions at work.
I see many comments here about Claude and I get the same feeling I get when I see comments about MacOS: it's nice that you're content with it, but I don't trust Apple/Anthropic for a fraction of an angstrom.
Wake me when we have ethically trained, open source models that run locally. Preferably high-quality ones.
btw how good are any of these tools for embedded programming? we need a new era for hardware enthusiasts. my dad made plenty of fun things in the 80s but it was at the tail end of the newess that came from radiokits and other gadgets that flooded the market due to the uchip
“Hell-ya brother”
100% agree even with half your experience.
all the insane and/or speculative projects that i never did because they would require heavy lift but with vague outcomes are now in progress. it's glorious.
I'm so excited to be able to continue build things when I'm living on the streets. I'm glad to know that drive to create will always be with me and keep me warm during winters.
You can't speak this kind of truth on hacker news!
But, uh, yeah... I've been noticing a growing divide between people like OP who are either already retired or are wealthy enough that they could if they wanted to who absolutely love the new world of LLMs, and people who aren't currently financially secure and realize that LLMs are going to snatch their career away. Maybe not this year, but not too far out either.
What I think is lost on ones like OP, is that yes, they are financially secure in the current climate. But if the future that everyone seems to be ushering in does come true, even ones like OP will be in a different state of security.
How does the saying go again? "It takes a village to reach financially secure retirement"
I’m on a field trip chaperoning my kid. I get a couple slack messages asking for some tweaks to a UI. I type a couple words into a Github AI Agent Session while riding the bus. Fixes are deployed to our staging env in 10 minutes.
Fucking wild.
try asking claude to write in VB6. Make some Active Server Pages. Use COM components. Why not? We can do things "better" now, but what does that matter when you can do the same things as before, but better?
I have bipolar disorder. The more frustrating aspects of coding have historically affected me tenfold (sometimes to the point of severe mania). Using Claude Code has been more like an accessibility tool in that regard. I no longer have to do the frustrating bits. Or at the very least, that aspect of the job is thoroughly diminished. And yes - coding is "fun again".
I think coding can be an endurance sport sometimes. There are a lot of points at which you have to bang your head against a wall for hours or days to figure out the smallest issue. Having an agent do that frustrating part definitely lowers the endurance needed to stay productive on a project.
Curious, what are you building?
exactly need some goal here ;)
Re-calibrate your bot
I've never built anything outside of a python notebook before, but Claude Code felt like magic to me.
I have this idea that probably violates some law of computing but I am really stubborn to make it happen somehow.
I want a game that generates its own mechanics on the fly using AI. Generates itself live.
Infinite game with infinite content. Not like no mans sky where everything is painfully predictable and schematic to a fault. No. Something that generates a whole method of generating. Some kind of ultra flexible communication protocol between engine and AI generator that is trained to program that protocol.
Develop it into a framework.
Use that framework to create one game. A dwarf fortress adventure mode 2.0
I have no other desires, I have no other goals, I don’t care. I or better yet - someone else, must do it.
I am 37;
Claude Code and it's parallels have extinguished multiple ones.
I was able to steer clear of the Bitcoin/NFT/Passport bros but it turns out they infiltrated the profession and their starry puppy delusional eyes are trying to tell me that iteration X of product Y released yesterday evening is "going to change everything".
They have started redefining what "I have build this" actually means, and they have outjerked the executives by slinging outrageous value creation narratives.
> I’m chasing the midnight hour and not getting any sleep.
You are 60; go spend some time with your grand-kids, smell a flower, touch grass forget chasing anything at this age cause a Tuesday like the others things are gonna wrap up.
Absolutely sincerely.
My main worry is: what is the license on the code produced by Claude (or any other coding agent)? It seems like, if it was trained using open-source software, then the resulting code needs to be open-source as well and it should be compatible with the original source. Artwork produced by an AI cannot be copyrighted, but apparently code can be?
If the software produced is for internal use, the point is probably moot. But if it isn't, this seems like a question that needs to be answered ASAP.
Building things as I read this.
Older here, equally excited. It's like programming with a team of your best buddies who are smarter than you but humble and eager to collaborate.
Perhaps I shouldn't say this but I feel that with the current LLMs I've found "my people" :)
This is the way. It's the most fun computers have been in decades.
"Just when I thought I was out, they pull me back in"