Hacker News Board Hacker News, browsed like a classic message board
Live data from Hacker News

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

twitter.com

Post reply on HN
Print view View original

371–380 of 630 posts

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

#371

Post by godelski »

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…

  > I'm now incentivized to use less abstractions.
I'd argue it's a different category of abstraction

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

#373

Post by zdragnar »

simonw wrote: post #336
zdragnar wrote: post #323

Earlier quoted context omitted.

That would go over on any decently sized team like a lead balloon.

As it should, normally, because "we'll rewrite it in React later" used to represent weeks if not months of massively disruptive work. I've seen migration projects like that push on for more than a year! The new normal isn't like that. Rewrite an existing cleanly implemented Vanilla JavaScript project (with tests) in React the kind of rote task you can throw at a coding agent like Claude Code and come back the next mo…

And everyone else's work has to be completely put on hold or thrown away because you did the whole thing all at once on your own.

That's definitely not something that goes over well on anything other than an incredibly trivial project.

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

#374

Post by remich »

simonw wrote: post #333
DrammBA wrote: post #332

Earlier quoted context omitted.

Simon, you're starting to sound super disconnected from reality, this "I hit everything that looks like a nail with my LLM hammer" vibe is new.

My habits have changed quite a bit with Opus 4.5 in the past month. I need to write about it..

Please do. I'm trying to help other devs in my company get more out of agentic coding, and I've noticed that not everyone is defaulting to Opus 4.5 or even Codex 5.2, and I'm not always able to give good examples to them for why they should. It would be great to have a blog post to point to…

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

#375

Post by indigodaddy »

simonw wrote: post #333
DrammBA wrote: post #332

Earlier quoted context omitted.

Simon, you're starting to sound super disconnected from reality, this "I hit everything that looks like a nail with my LLM hammer" vibe is new.

My habits have changed quite a bit with Opus 4.5 in the past month. I need to write about it..

Can you expound on Opus 4.5 a little? Is it so good that it's basically a superpower now? How does it differ from your previous LLM usage?

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

#376

Post by hamstergene »

I feel like many people in the comments aren't aware that Karpathy is an ML scientist for whom programming is a complementary skill, not a profession. The only reason he came up with "vibe coding" is because maximum complexity of his hobby projects made it seem believable. Maybe take his opinions about fate of programming with a grain of salt.

He is brilliant no doubt, but not in that field.

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

#377

Post by godelski »

simonw wrote: post #333
DrammBA wrote: post #332

Earlier quoted context omitted.

Simon, you're starting to sound super disconnected from reality, this "I hit everything that looks like a nail with my LLM hammer" vibe is new.

My habits have changed quite a bit with Opus 4.5 in the past month. I need to write about it..

What's concerning to many of us is that you've (and others) have said this same thing s/Opus 4.5/some other model/

That feels more like chasing than a clear line of improvement. It's interrupted very different from something like "my habits have changed quite a bit since reading The Art of Computer Programming". They're categorically different.

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

#378

Post by throwatdem12311 »

deadbabe wrote: post #364
throwatdem12311 wrote: post #282

Earlier quoted context omitted.

I have a hell of a time just getting any LLM to write SQL queries that have things like window functions, aggregates and lateral left joins - even when shoving the entire database schema DDL into the context. It's so frustrating, it regularly makes me want to just quit the profession. Which is why I still just write most code by hand.

If you really know SQL, writing an SQL query basically just feels like writing a prompt for a database client anyway, except it does exactly what you ask for.

I have a running joke at work.

* LLMs are just matrix multiplication. * SQL is just algebra, which has matrix multiplication as part of it. * Therefore SQL is AI * Now who is ready to invest a billion dollars in our AI SaaS company?

Or it’s just that astronaut with a gun meme: “Wait AI is just SQL?….Alway has been.”

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

#379

Post by data-ottawa »

throwatdem12311 wrote: post #282
superze wrote: post #40

As an Opus user, I genuinely don’t understand how someone can work for weeks or months without regularly opening an IDE. The output almost always fails. I repeatedly rewrite prompts, restate the same constraints, and write detailed acceptance criteria, yet still end up with broken or non-functional code.its very frustrating to say the least Yesterday alone I spent about $200 on generations that now require significan…

I have a hell of a time just getting any LLM to write SQL queries that have things like window functions, aggregates and lateral left joins - even when shoving the entire database schema DDL into the context. It's so frustrating, it regularly makes me want to just quit the profession. Which is why I still just write most code by hand.

I write a lot of SQL and I haven't had these issues for months, even with smaller models. Opus can one shot most of my queries faster than I could type them.

Instead of stuffing the context with DDL I suggest:

1. Reorganize your data warehouse. It needs to be easy to find the correct data. Make sure you use ELT clear layers, meaningful schemas, and have per-model documentation. This is a ton of work, but if done right the payoff is massive.

2. I built a tool for myself to pull our warehouse into a graph for fuzzy search+dependency chain analysis. In the spring I made an MCP server for it and Claude uses that tool incredibly well for almost all queries. I haven't actually used the GUI or scripts since I built the MCP.

Claude and Devstral are the best models I've used for SQL. I cannot get Gemini to write decent modern sql -- even the Gemini data science/engineer agents in Google Cloud. I occasionally try the paid models through the API and still haven't been impressed.

Post reply on HN