←back to thread

Andrej Karpathy: Software in the era of AI [video]

(www.youtube.com)
1480 points sandslash | 4 comments | 19 Jun 25 00:33 UTC | HN request time: 0.704s | source
Show context
abdullin ◴[19 Jun 25 07:03 UTC] No.44316210[source]▶
Tight feedback loops are the key in working productively with software. I see that in codebases up to 700k lines of code (legacy 30yo 4GL ERP systems).

The best part is that AI-driven systems are fine with running even more tight loops than what a sane human would tolerate.

Eg. running full linting, testing and E2E/simulation suite after any minor change. Or generating 4 versions of PR for the same task so that the human could just pick the best one.

replies(7): >>44316306 #>>44316946 #>>44317531 #>>44317792 #>>44318080 #>>44318246 #>>44318794 #
latexr ◴[19 Jun 25 11:54 UTC] No.44317792[source]▶
> Or generating 4 versions of PR for the same task so that the human could just pick the best one.

That sounds awful. A truly terrible and demotivating way to work and produce anything of real quality. Why are we doing this to ourselves and embracing it?

A few years ago, it would have been seen as a joke to say “the future of software development will be to have a million monkey interns banging on one million keyboards and submit a million PRs, then choose one”. Today, it’s lauded as a brilliant business and cost-saving idea.

We’re beyond doomed. The first major catastrophe caused by sloppy AI code can’t come soon enough. The sooner it happens, the better chance we have to self-correct.

replies(6): >>44317876 #>>44317884 #>>44317997 #>>44318175 #>>44318235 #>>44318625 #
koakuma-chan ◴[19 Jun 25 12:25 UTC] No.44317997[source]▶
> That sounds awful. A truly terrible and demotivating way to work and produce anything of real quality

This is the right way to work with generative AI, and it already is an extremely common and established practice when working with image generation.

replies(3): >>44318041 #>>44318110 #>>44318310 #
notTooFarGone ◴[19 Jun 25 12:32 UTC] No.44318041[source]▶
I can recognize images in one look.

How about that 400 Line change that touches 7 files?

replies(3): >>44318098 #>>44318227 #>>44318814 #
1. mistersquid ◴[19 Jun 25 14:07 UTC] No.44318814[source]▶
> I can recognize images in one look.

> How about that 400 Line change that touches 7 files?

Karpathy discusses this discrepancy. In his estimation LLMs currently do not have a UI comparable to 1970s CLI. Today, LLMs output text and text does not leverage the human brain’s ability to ingest visually coded information, literally, at a glance.

Karpathy surmises UIs for LLMs are coming and I suspect he’s correct.

replies(1): >>44319905 #
2. variadix ◴[19 Jun 25 16:02 UTC] No.44319905[source]▶
The thing required isn’t a GUI for LLMs, it’s a visual model of code that captures all the behavior and is a useful representation to a human. People have floated this idea before LLMs, but as far as I know there isn’t any real progress, probably because it isn’t feasible. There’s so much intricacy and detail in software (and getting it even slightly wrong can be catastrophic), any representation that can capture said detail isn’t going to be interpretable at a glance.
replies(2): >>44320927 #>>44322430 #
3. mistersquid ◴[19 Jun 25 17:52 UTC] No.44320927[source]▶
> The thing required isn’t a GUI for LLMs, it’s a visual model of code that captures all the behavior and is a useful representation to a human.

The visual representation that would be useful to humans is what Karpathy means by “GUI for LLMs”.

4. skydhash ◴[19 Jun 25 20:50 UTC] No.44322430[source]▶
There’s no visual model for code as code isn’t 2d. There’s 2 mechanism in the turing machine model: a state machine and a linear representation of code and data. The 2d representation of state machine has no significance and the linear aspect of code and data is hiding more dimensions. We invented more abstractions, but nothing that map to a visual representation.