There are priorities here which are not mutually exclusive. If you are building the next big thing in your garage, polishing it before establishing it's in fact the next big thing is a waste of time. If it really is, early adopters / investors will seize on it like they did on AI. Once that is established, yes there is space for adults in the room to adopt proper procedures for large scale production. I do believe AI can help with establishing the next big thing, and if other's don't, it's a irreconcilable difference of opinion.

Agreed. I really don’t think this is worth arguing that AI can be a huge help. I was skeptical until April even after hearing many friends tell me how good Opus 4.5 was last year.

Not working on the “next big” thing but I only recently started finding that AI could solve complex problems for me starting around ChatGPT 5.5. Working on a game engine. Some of the quite isolated modules I’ve had it build are not good code by my own standards. The code has way too many indirections to say the least. But they work without bugs and perform well too (i have a very good CPU and memory management harness for my frame loop). My velocity on the project has doubled at least cause now stuff that I wanted to do down the line is already done. I’m definitely a bit careful with setting up isolated guardlines about which files I let a certain feature touch but with models like Fable even found that unnecessary.

Working code that performs exactly how I want on an outer level is valuable. It can be refactored and rearchitected or reimplemented better by just the virtue of having something to compare against and having the edge cases accounted for.

One of the first things I do before spending time with a coding agent on generating something is having a pretty long reasoning session where I pressure the agent to find out if the problem I'm solving has been solved before, at all, in any way. Most of the time, it has, and it probably doesn't have utility beyond my own personal education in solving it again.

That seems to be what most of these projects that get accused of being "vibe coded" are doing. Incidentally - there's nothing wrong with writing your own useful utilities, and educational to package these up for distribution/release, but don't be surprised if not another soul in the world finds the particular need you had to be one they share.

It's much, much more nuanced than that.

On one hand, it's very good advice to be clear about PMF. If you have to ask your product doesn't have it. It'll be servers-on-fire obvious when you reach product-market-fit.

On the other hand two things stick out: 1) for every example that proves polishing doesn't matter, there's a successful exception that broke every rule and succeeded anyway. The founder of Figma for example, said he worked on its foundation for something like 4 years before launching. 2) Internet, consumer tech, mobile, sass are all mature markets and the quality bar is very high at this point. It's not obvious that some novel concept will be enough to overcome sheer inertia of status-quo incumbents.

> If you are building the next big thing in your garage, polishing it before establishing it's in fact the next big thing is a waste of time.

Ideas are cheap. The execution matters and you need to polish it at least until certain level.

There are amputees that do snowboarding with specially designed prosthesis and boards, so there is certainly a way to take load off weak knees with appropriate gear. OP is just, quite reasonably, not prioritizing this minor dream enough to invest so much time and money in it at the expense of other priorities.

Does "athlete" in your original post have to be only martial art/contact sports? For example, are you medically unable to do absolutely any strength exercises, maybe upper body only, with appropriate support/isolation? A lot of times it's a matter or re framing rather than giving up goals, a lot can be done at home with a pair of adjustable dumbbells.

Lean into medicine, tech and science? Zepbound + strength training is a life transforming miracle and they are coming up with even more effective drugs and modern AI deep research (think coding agent pouring over mountains of data) is amazing at coming up with an investment plan to eventually own a home, for example putting up a downpayment and running a rental in a really cheap area and then eventually using income to finance something more convenient if you are not willing to move.

My point is not that all problems can be solved, but I think what OP is saying is that life is a matter of focus. I am putting plans of a soaring corporate career on ice not because I am 100% sure I couldn't swing it but because trying to would take focus away from things I want more like lifting heavy weights and tinkering with tech at home. But for absolute top priorities, I don't think it's ever worth giving up on the concept. Hard limits can be handled by reframing what success looks like and path to get there, not giving up on the essence.

Just don't blame me if your coding agent curses CEO and bypasses presubmits with dirty hacks a year later, I never volunteered to be a role model.

That blog post is human prompted, anyone who has experience with AI knows the difference between AI originated content (tables and bullet points) and AI spicing up a human prompt with detailed roasting instructions. Been there, done that (harmlessly like mocking concepts not targetting individuals).

You just need to work on your agent design and prompting skills, modern LLMs are crazy good at all the things you listed with the right context and tools.

Technically yes, but this has nothing to do with LLMs.

You need to be able to write a good spec period, and this has been true as long as programming has existed. The problem is, LLMs cannot write them themselves, and have trouble reasoning out the unstated parts of complex problems if the spec doesn't spell it out.

Developers familiar with the problem space being worked on, however, can reason out the unstated parts, because the unstated parts are usually the bread and butter of the problem space.

Side note: this is often why LLMs trained on synthetic text perform weirdly or badly... the synthetic text is written by people not familiar with the thousands of individual problem spaces that exist out there, and miss important facts or nuance.

LLMs trained on real text, however, is often done without proper license, and are essentially lossy compressed piracy archives. You're damned if you do, you're damned if you don't.