If you are capable of being a leonardo, then this approach will work.

Not everyone is capable of being Leonardo

  > see Bill Gate's famous quote about hiring lazy people

Fewer and fewer people I know are actually passionate about programming and it's not uncommon to see people be burned out and just want to do their 9-5. And I see a strong correlation with these people embracing AI. It makes sense if you don't care and are just trying to get the job done. I don't think it's surprising things are getting buggier and innovation slowed. We killed the passion and tried to turn it into a mechanical endeavor. It's a negative feedback loop

It's a fundamentally flawed analogy. Leo's apprentices learned and improved. They studied under a master and faced serious repercussions if they bullshitted about their ability or what they had accompolished.

LLM capabilities are tied to their model, and won't improve on their own. You learn the quirks of prompting them, but they have fixed levels of skill. They don't lie, because they don't understand concepts such as truth or deception, but that means they'll spout bullshit and it's up to you to review everything with a skeptical eye.

In this analogy, you aren't the master, you're one part client demanding work, one part the janitor cleaning up after their mistakes.

So what does that amount to? Shared Claude code hooks and skills?

[dead]

Professionally, I do banking. It's a lot of integration work, sprinkled with a little algorithm every now and then. Lately I've been on capital requirements. The core of that is a system called AxiomSL, which is quite a lot of work for one guy to keep running.

In my spare time I write some algorithmic C, you can check that stuff out on github (https://github.com/DelusionalLogic) if you're curious.

I was an early adoter of LLM's. I used to lurk in the old EleutherAI discord and monitor their progress in reconstructing GPT-2 (I recall it being called GPT-J). I also played around a bunch with image generation. At this point nobody really tried applying them to code. We were just fascinated that it wrote back at all.

I have tried most of the modern models for development. I find then to generate a lot of nonsensical and unexplainable code. I've had no success (in the 30 or so times I've tried) at getting any of the models to debug or develop even small features. They usually get lost in some "best practice" and start looping on that forever. They're also constantly breaking style and violating module boundaries.

If i use them to generate documentation I find it to be surface level and repetitive. It'll make a lot of text about structures that are obvious to me just glancing at the code, but will (obviously) not have any context about the thought process that created that code, which is the only part I care about. I can read the code just fine myself. This is the same problem I find in commit messages generated with AI tools.

For the reversing I also do, I find the models to be too imprecise. It'll take large logical leaps that ruin understanding of the code I'm trying to understand. This is the only place I actually believe a properly trained (not a chatbot) model could actually succeed past the state of the art.

I don't really use stackoverflow either, I don't trust its accuracy, and it's easy to get cargo culted in software. I generally try to find my answers in official documentation, and if I can't get that I'll read the source code. If that's unavailable I'll take a guess, or reverse the thing If it's really important to me.

100 times? You do in a day what used to take you 3 months?

Those are just not realistic numbers.

I think it depends on the project and the context, but I developed my own task management system particularly because of this challenge. I'm starting to extend this with verification gates as well.

If I worked on different types of systems with different types of tasks I might feel the same way as you, i think AI works well in specific targeted use cases, where some amount of hallucination can be tolerated and addressed.

What models are you using, I use opus 4.5, which can one shot a surprising ratio of tasks.

If you can predict that hitting “summarize conversation” equals rework, what can you change upstream so you avoid triggering it? Are you relying on the agent to carry state instead of dumping it into .MD files? What happens if your computer crashes?

> so it the model isn't the cause

Thing is, the prompts, those stupid little bits of English that can't possiu matter all that much? It turns out they affect the models performance a ton.

I lazily delegate things that can be automated, which frees me up to do actual feature development.

> I want to spend my life pursuing mastery of a craft, not lazily delegating.

And yet, the Renaissance "grand masters" became known as masters through systematizing delegation:

https://smarthistory.org/workshop-italian-renaissance-art/