Karpathy on Programming: “I've never felt this much behind”

Post by Trasmatta » Tue, Dec 30, 2025, 12:54 AM UTC

AndrewKemendo wrote: post #111

rambojohnson wrote: post #58

What exhausts me isn’t “falling behind.” It’s watching the profession collectively decide that the solution to uncertainty is to pile abstraction on top of abstraction until no one can explain what’s actually happening anymore. This agentic arms race by C-suite know-nothings feels less like leverage and more like denial. We took a stochastic text generator, noticed it lies confidently, wipes entire databases and hard…

Every technical person has been complaining about this for the entire history of computer programming Unless you’re writing literal memory instructions then you’re operating on between 4 and 10 levels of abstraction already as an engineer It has never been tractable for humans to program a series of switches without incredible number of abstractions The vast majority of programmers never understood how computers work…

Post by krackers » Tue, Dec 30, 2025, 12:59 AM UTC

davesque wrote: post #230

Honestly surprised at this take by him. For one, feels like exaggeration. For two, are these tools really that hard to use?

Post by cygn » Tue, Dec 30, 2025, 1:00 AM UTC

tehnub wrote: post #260

qudat wrote: post #177

Earlier quoted context omitted.

As far as I can tell as a heavy coding agent user: you don’t need to know any of this and that’s a testament to how good code agent TUIs have become. All I do to be productive with a coding agent is tell it to break a problem down into tasks, store it inside beads, and then make sure each step is approved by me. I also add in a TDD requirement where it needs to build tests that fail then eventually pass. Everything e…

Beads?

Post by nkrisc » Tue, Dec 30, 2025, 1:03 AM UTC

simonw wrote: post #100

rambojohnson wrote: post #58

What exhausts me isn’t “falling behind.” It’s watching the profession collectively decide that the solution to uncertainty is to pile abstraction on top of abstraction until no one can explain what’s actually happening anymore. This agentic arms race by C-suite know-nothings feels less like leverage and more like denial. We took a stochastic text generator, noticed it lies confidently, wipes entire databases and hard…

I think AI-assisted programming may be having the opposite effect, at least for me. I'm now incentivized to use less abstractions. Why do we code with React? It's because synchronizing state between a UI and a data model is difficult and it's easy to make mistakes, so it's worth paying the React complexity/page-weight tax in order for a "better developer experience" that allows us to build working, reliable software…

Post by simonw » Tue, Dec 30, 2025, 1:04 AM UTC

all_factz wrote: post #296

simonw wrote: post #208

Earlier quoted context omitted.

I'm not arguing for using LLMs as an abstraction. I'm saying that a key component of the dependency calculation has changed. It used to be that one of the most influential facts affecting your decision to add a new library was the cost of writing the subset of code that you needed yourself. If writing that code and the accompanying tests represented more than an hour of work, a library was usually a better investment…

React is hundreds of thousands of lines of code (or millions - I haven’t looked in awhile). Sure, you can start by having the LLM create a simple way to sync state across components, but in a serious project you’re going to run into edge-cases that cause the complexity of your LLM-built library to keep growing. There may come a point at which the complexity grows to such a point that the LLM itself can’t maintain the…