Worse, you’re doing code review of poorly written code with random failure modes no human would create, and an increasingly big ball of mud that is unmaintainable over time. It’s just the worst kind of reviewing imaginable. The AI makes an indecipherable mess, and you have to work out what the hell is going on.
My codebase is a zen garden I've been raking for 6 years. I have concerns about what's going to happen after a few months of "we're using AI cause they told us to."
You'd be surprised what you can do with Claude Code. Pick any mature programming language, including niche ones like Ada and treat the project seriously. Write detailed agent files, features spec files, start from the bottom with CI/CD and set up a test suite, coding guidelines, static analysis. Be careful to create a consistent architecture and code base early.
You'll get a lot further and faster than you'd expect.
Things will probably plateau as you master the new tech, but it's possible you'll not write a ton of code manually along the way.
Oh, your general software development experience should help with debugging the weird corner cases.
I imagine it's really hard to do this with 0 software dev experience, for example. Yeah, you'll build some simple things but you'll need and entire tech education to put anything complex in prod.
Using Claude code Pro with a maxed subscription and ChatGPT Codex with the business subscription.
The code is written in Dart and never wrote a line of DART in my life, I'm a veteran expert around Java, C++. The reason for choosing DART is simply because it is way readier for multi-platform contexts than Java/C++. The same code base now runs on Linux, Android, iOS, OSX, Windows and Web (as static HTML). Plus the companion code in C++ for ESP32 microcontrollers. It also includes a CLI for running as linux server.
Don't ask me for a hard analysis and data proving x25 performance increase, what I know is that an off-grid product was previously taking me two years of research/effort to build in Android/Web and get a prototype running. Now in about a month went far above all previous expectations (cached maps with satellite imagery, bluetooth mesh, webRTC, whatever apps) and was able to release a product several times per day that works as envisioned. Iterating quickly and getting direct feedback from users.
IMHO, Codex is far superior at the moment for complex tasks, Claude is cheaper and still good enough quality for most tasks. In addition to keep several terminals with tasks in parallel, this gives me time throughout the day for other tasks with family/friends and a lot of motivation like a coding-buddy to try different routes and quickly implement a prototype instead of always being alone doing this kind of work. For example, it added an offline GPT bot but wasn't what was needed so could quickly discard it too.
These tools get lost on API implementations and the documentation folder is mostly there to provide the right context when needed. I've learned to use simple markdown documents with things to keep in mind like "reusable.md" or "API.md" to make sure it won't reinvent them. Given my experience, there are parts that I'd implement with higher quality on my own, the trade-off is that I can't touch the code by myself now. One of the reasons is that it would make more difficult for these AI to work since my naming and file structure would make it difficult for the AI to work with, the other reason is because I don't want to waste a full day on a single problem like before. As the product grows more stable is when more attention is given to the finer details. On early stages, that type of quality is still more than good enough for me.
You can try the Android or Linux versions if you are so inclined. Never in my life would I ever be able to build so much in 5 weeks.
Would you describe this product as a whole application suite (blogging, calendar, commerce) plus its own backend infrastructure that is capable of serving these apps to the public internet and functioning offline via ad-hoc wireless peer-to-peer, with a cryptographic layer providing identity, security and censorship resistance, and that runs on phone, laptop or raspberry pi?
Quite ambitious.
Is this an LLM hallucinating? taking a break from coding? or leaking your personal desktop session?
I find your essay more downbeat. I actually disagree with it too, as it misses the fact that children aren’t really aware of their lives in the same way adults are. Life begins at 18 imo.
I’m about to become a parent, about 10 years later than I’d have liked. Main reason for that is just not meeting the right person, pandemic, money etc.
But I only feel ready now. I’m a late developer in general (aren’t all software engineers haha arf) and I honestly felt too free spirited in the past. Many friends had kids a decade or more ago, and they are looking forward to their kids leaving home so they can travel etc. But I’ve already done all that, I have nothing to devote my life to now other than work and family.
In my case at least, being ready was a real thing. It’s really about maturity and having had enough of a life myself.
Are they truly happier, in the sense of being more content? Or are they just deriving more temporary pleasure from the hedonic treadmill they're on?
You can probably tell which one it is, by how long their happiness with their house / car / TV / fill-in-the-blank lasts, before they start thinking about trading up to an even nicer fill-in-the-blank.
Buddhist monk Matthieu Ricard wrote a great book on happiness, here's an excerpt I enjoy which talks about the difference between pleasure and happiness, in two parts. [1] [2]
Fair enough on the personal decision part. I'm less interested in telling people what to do and more interested in whether the premise ('nicer things = happier') actually tracks with how human satisfaction works. The research suggests it often doesn't, which seems worth knowing regardless of what you choose to do with that information. [1]
I would recommend the recently published book The Art of Spending Money by Morgan Housel, or check out the interviews he's done in recent months on it:
It's not about being frugal or cheap or spendy, but on recognizing human psychology and what actually brings most people happiness. See also the 85-year Harvard study on the topic:
Maslow's hierarchy of needs would assume that there is a point beyond which extra material comfort does not make you happy or content, but it also is quite clear that there is a point at up to which it does. Most books on happiness are written for people who are long past the point where increasing their monetary inputs will increase their happiness and contentment, but it is also clear those people exist and are perhaps even in the majority of humanity.
I really don't like this moralizing but more importantly there's increasing evidence that wealth does correlate with life satisfaction.
> The data showed the happiness gap between wealthy and middle-income participants was wider than between middle- and low-income participants.
And the apparent reason:
> He said: “A greater feeling of control over life can explain about 75% of the association between money and happiness. So I think a big part of what’s happening is that, when people have more money, they have more control over their lives. More freedom to live the life they want to live.”
Sure, but I’d argue that it’s largely reduced stress rather than raw materialism. For example being able not to worry about paying both the electric bill and a child’s dental work this month.
There’s many other research that corroborates this view. After some point increasing income didn’t increase life satisfaction. Usually somewhere in the low upper-middle class region.
> After some point increasing income didn’t increase life satisfaction. Usually somewhere in the low upper-middle class region.
That's the common assumption that this research repudiates.
> These findings are counter to a widely covered 2010 study that found happiness rises with income, but plateaus at around $75,000.
He studied much richer people:
> Killingsworth also used data from the ultra-wealthy (people with a median net worth between $3m and $7.9m), which is often lacking and difficult to obtain.
> The data showed the happiness gap between wealthy and middle-income participants was wider than between middle- and low-income participants.
> His study also found wealthy individuals were “substantially and statistically significantly happier than people earning over $500,000 each year”.
> Are they truly happier, in the sense of being more content?
The biggest thing anyone can do in their life is figure out exactly what makes them happy, and spend their money there. Don't let society tell you. People on this site likely care about computers and spend a disproportionate amount of their money on them, and that's ok. I don't care about cars or TVs, but I care about experiences and comfort so will spend money on travel and upgraded plane tickets.
I also care about agency, so tend to save money rather than spend. I want the freedom it provides more than what it can buy - typically.
Yeah but what is meaningfully "nicer" becomes and exponentially more expensive and ends up being mostly wasted value. And by time someone has to start actually worrying about such questions they have enough free capital to spend that they can have a high quality version of almost anything anyone would want to possess or use other than pure displays of wealth.
Maybe if the basic needs on the average person were taken care of then random displays of extravagant wealth would be acceptable. But when something as simple as getting a rotten tooth extracted or a filling on a front tooth is too much "luxury" for many working class citizens, it is a complete misallocation of society's resources.
I'm happy right after I eat ice cream too. Doesn't make it a good lifestyle.
Before you go on about how saying it's "good" or "not good" is a value judgement that I'm not entitled to make -- you're damn right it is, and I'll do what I want.
My 14" portable CRT I had when I was a teenager gave me joy every time I used it. My first car cost me less than 2k and gave me joy for 5 years.
You are now unable to get joy from a TV smaller than the largest one you've ever bought. Many people are unable to get joy from a car costing under 10k, let alone 2k.
It is actually the opposite. The less things you have, the less things you will want.
I even experience this with food. If I am on a strict diet for 2 weeks and then have a "cheat" meal, a previously normal meal feels like a satisfying feast.
If I splurge on food for 2 weeks, even 3/4th a pizza doesn't satisfy. I just want the other 1/4th.
It is really why we have so much wealth as a society but so much discontent. It is like believing there is some amount of alcohol that would satisfy the alcoholic. It just grows the desire for more while contentment is harder and harder to achieve.
I am pretty sure this is just a property of the dopaminergic system.
> You can buy a bigger and bigger house car tv stereo whatever
> But you can do that without any money.
Well...
Material things can contribute to happiness, or detract.
Balancing the things we spend our life on, relative to an understanding of what makes us happy, is going to be an idiosyncratic exercise. Assuming that X won't contribute to the happiness of person Y is some deep projection.
There seem to be many kinds of happiness too. Would I remain happy if I lost my house? Yes. I have gone through enough ups and downs to know that. But would I feel as fulfilled? No. I have gone through enough ups and downs to know that.
It's true (I live in Omaha). He is still in the same house.
I didn't grow up here—my wife did. Very early on, when I first visited Omaha, she drove me by his place. After three decades or so in California, I retired and we moved back to her hometown. Buffett is still there.
I went by it a few weeks ago. There's a gate on the driveway, and I assume some kind of security presence. Probably no different than anyone under constant public scrutiny.
I own several and have ridden thousands upon thousands of miles.
When I got my first bike as a kid, a cheap "mountain bike" with 24" wheels that probably weighed more than my current road bike, I was at maximum happiness. I was not at only 40% happiness because it didn't have a carbon frame or a Di2 groupset from the future. I was at 100.
Later when I got my first road bike I was at 100% happiness again. But nothing can make me happier than I was with that first, heavy bicycle-shaped object. It might equal it but it's impossible to surpass.
Nowhere did anybody say “moving house for any reason is bad”. Buffet could’ve moved if he wanted to, I presume. So, evidently, he didn’t have any of those ‘other reasons’. What we *can^ say is that he didn’t move, which shows that he didn’t allow lifestyle inflation to extend to his place of residence.
No they said we can all learn from it. I understood the implication, I just reject the stated idea that that lesson is to “live in one house for your entire adult life”.
> You can buy a bigger and bigger house car tv stereo whatever, but it will not make you happy.
Hard disagree here.
Ask a 4 person family stuffed into a one bedroom condo if buying a larger 3 bedroom home would make them happier, I'd imagine to 99.99999% of them the answer is yes.
I upgraded my road bike 2 years ago from an entry level one to a nice racing bike and each weekend I ride a 100km route, that sure as heck makes me happier than riding the old slower and heavier bike.
We just took our extended family on a vacation for a week. Money sure as heck made us happier in that instance.
It is true that cash can't fix all issues in life but any one who says money can't make you happy is either lying or doesn't have money.
Run a simple thought experiment in your head. If you woke up tomorrow under crushing credit card and medical debt and it was suddenly paid off, would that make you happier?
Meh. If you have the resources, buy whatever makes you happy.
If a bigger house makes you happy because you have space for your hobbies and you don't need to fight with your family members for space, buy a bigger house.
The whole "money doesn't bring happiness" thing is bullshit unless you are a Buddha.
A mansion in Malibu isn't going to make me happy, because I wouldn't know what the hell to do in Malibu. An upgrade from a 2-bedroom to a 4-bedroom home with a garage so I don't have to smell laser cutter fumes anymore and hack a ventilation system out a bedroom window? That very well might.
> An upgrade from a 2-bedroom to a 4-bedroom home with a garage so I don't have to smell laser cutter fumes anymore and hack a ventilation system out a bedroom window? That very well might.
As someone who upgraded from a 2 bedroom flat to a 3 bedroom house with a garage, I concur. Having a place to store my bikes and other “dirty” tools that’s not inside was such an improvement to my quality of life that I tell people to always look for a half decent garage when they buy. Especially if they also like cycling!
Firstly, reading is actually a bit boring and unpleasurable at first. Only once you’ve gotten up to speed does it start rewarding you. A bit like working out at the gym.
The other surprise is that once you start reading, you get really quick. Like, surprisingly fast. After a while you notice the words are going by faster. So the effort compounds.
When you start you think “my god that took 5 hours of boring reading time to get though” and by book 10 you think “that was 2.5 hours and I learnt a lot and my brain is happy.”
It’s also possible that people more experienced, knowledgable and skilled than you can see fundamental flaws in using LLMs for software engineering that you cannot. I am not including myself in that category.
I’m personally honestly undecided. I’ve been coding for over 30 years and know something like 25 languages. I’ve taught programming to postgrad level, and built prototype AI systems that foreshadowed LLMs, I’ve written everything from embedded systems to enterprise, web, mainframes, real time, physics simulation and research software. I would consider myself an 7/10 or 8/10 coder.
A lot of folks I know are better coders. To put my experience into context: one guy in my year at uni wrote one of the world’s most famous crypto systems; another wrote large portions of some of the most successful games of the last few decades. So I’ve grown up surrounded by geniuses, basically, and whilst I’ve been lectured by true greats I’m humble enough to recognise I don’t bleed code like they do. I’m just a dabbler. But it irks me that a lot of folks using AI profess it’s the future but don’t really know anything about coding compared to these folks. Not to be a Luddite - they are the first people to adopt new languages and techniques, but they also are super sceptical about anything that smells remotely like bullshit.
One of the most wise insights in coding is the aphorism“beware the enthusiasm of the recently converted.” And I see that so much with AI. I’ve seen it with compilers, with IDEs, paradigms, and languages.
I’ve been experimenting a lot with AI, and I’ve found it fantastic for comprehending poor code written by others. I’ve also found it great for bouncing ideas. And the code it writes, beyond boiler plate, is hot garbage. It doesn’t properly reason, it can’t design architecture, it can’t write code that is comprehensible to other programmers, and treating it as a “black box to be manipulated by AI” just leads to dead ends that can’t be escaped, terrible decisions that will take huge amounts of expert coding time to undo, subtle bugs that AI can’t fix and are super hard to spot, and often you can’t understand their code enough to fix them, and security nightmares.
Testing is insufficient for good code. Humans write code in a way that is designed for general correctness. AI does not, at least not yet.
I do think these problems can be solved. I think we probably need automated reasoning systems, or else vastly improved LLMs that border on automated reasoning much like humans do. Could be a year. Could be a decade. But right now these tools don’t work well. Great for vibe coding, prototyping, analysis, review, bouncing ideas.
reply