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

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

youtube.com

Post reply on HN
Print view View original

451–460 of 827 posts

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

#451

Post by necrodome »

diggan wrote: post #200
necrodome wrote: post #68

Earlier quoted context omitted.

We ( https://vibes.diy/ ) are betting on this

Border-line off-topic, but since you're flagrantly self-promoting, might as well add some more rule breakage to it. You know websites/apps who let you enter text/details and then not displaying sign in/up screen until you submit it, so you feel like "Oh but I already filled it out, might as well sign up"? They really suck, big time! It's disingenuous, misleading and wastes people's time. I had no interest in using yo…

Thanks for the benefit of the doubt. I typed that in a hurry, and it didn’t come out the way I intended.

We had the idea that there’s a class of apps [1] that could really benefit from our tooling - mainly Fireproof, our local-first database, along with embedded LLM calling and image generation support. The app itself is open source, and the hosted version is free.

Initially, there was no login or signup - you could just generate an app right away. We knew that came with risks, but we wanted to explore what a truly frictionless experience could look like. Unfortunately, it didn’t take long for our LLM keys to start getting scraped, so the next best step was to implement rate limiting in the hosted version.

[1] https://tools.simonwillison.net/

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

#452

Post by tudorizer »

oc1 wrote: post #440
tudorizer wrote: post #405

95% terrible expression of the landscape, 5% neatly dumbed down analogies. English is a terrible language for deterministic outcomes in complex/complicated systems. Vibe coders won't understand this until they are 2 years into building the thing. LLMs have their merits and he sometimes aludes to them, although it almost feels accidental. Also, you don't spend years studying computer science to learn the language/synt…

AI is all about context window. If you figured out the context problem, you will see that all these "AI is bullshit, it doesn't work and can't produce working code" goes away. Same for everything else.

Working code or not is irelevant. Heck, even human-in-loop (Tony-in-the-Iron-Man) is not actively the point. If we're going into "it's all about" territory then it's all about:

- training data - approximation of the desired outcome

Neither support a good direction for the complexity of some of the system around us, most of which require dedicated language. Imagine doing calculus or quantum physics in English. Novels of words would barely suffice.

So a context window as big as the training data itself?

What if the training data is faulty?

I'm confident you understand that working code or not doesn't matter in this analogy. Neither does LLMs reaching out for the right tool.

LLMs has its merits. Replacing concrete systems that require a formal language and grammar is not.

`1 + 1 = 2` because that's how maths works, not because of deja vú.

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

#453

Post by mkleczek »

kordlessagain wrote: post #414
practal wrote: post #50

Great talk, thanks for putting it online so quickly. I liked the idea of making the generation / verification loop go brrr, and one way to do this is to make verification not just a human task, but a machine task, where possible. Yes, I am talking about formal verification, of course! That also goes nicely together with "keeping the AI on a tight leash". It seems to clash though with "English is the new programming l…

This thread perfectly captures what Karpathy was getting at. We're witnessing a fundamental shift where the interface to computing is changing from formal syntax to natural language. But you can see people struggling to let go of the formal foundations they've built their careers on.

This is why I call all this AI stuff BS.

Using a formal language is a feature, not a bug. It is a cornerstone of all human engineering and scientific activity and is the _reason_ why these disciplines are successful.

What you are describing (ie. ditching formal and using natural language) is moving humanity back towards magical thinking, shamanism and witchcraft.

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

#454

Post by diggan »

jes5199 wrote: post #434

okay I’m practicing my new spiel: this focus on coding is the wrong level of abstraction coding is no longer the problem. the problem is getting the right context to the coding agent. this is much, much harder “vibe coding” is the new “horseless carriage” the job of the human engineer is “context wrangling”

> coding is no longer the problem.

"Coding" - The art of literally using your fingers to type weird characters into a computer, was never a problem developers had.

The problem has always been understanding and communication, and neither of those have been solved at this moment. If anything, they have gotten even more important, as usually humans can infer things or pick up stuff by experience, but LLMs cannot, and you have to be very precise and exact about what you're telling them.

And so the problem remains the same. "How do I communicate what I want to this person, while keeping the context as small as possible as to not overflow, yet extensive enough to cover everything?" except you're sending it to endpoint A instead of endpoint B.

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

#455

Post by bsenftner »

sensanaty wrote: post #316
bsenftner wrote: post #260

Earlier quoted context omitted.

I'm a greybeard, 45+ years coding, including active in AI during the mid 80's and used it when it applied throughout my entire career. That career being media and animation production backends, where the work is both at the technical and creative edge. I currently have an AI integrated office suite, which has attorneys, professional writers, and political activists using the system. It is office software, word proces…

So AI is simultaneously going to take over everyone's job and do literally everything, including being used as application UI somehow... But you have to talk to it like a moody teenager at their first job lest you get nothing but garbage? I have to put just as much (and usually, more) effort talking to this non-deterministic black box as I would to an intern who joined a week ago to get anything usable out of it? Yea…

Consider that these AIs are trained on human communications, they mirror that communication. They are literally damaged document repair models, they use what they are given to generate a response - statistically. The fact that a question generates text that appears like an answer is an exploited coincidence.

It's a perspective shift few seem to have considered: if one wants an expert software developer from their AI, they need to create an expert software developer's context by using expert developer terminology that is present in the training data.

One can take this to an extreme, and it works: read the source code of an open source project and get and idea of both the developer and their coding style. Write prompts that mimic both the developer and their project, and you'll find that the AI's context now can discuss that project with surprising detail. This is because that project is in the training data, the project is also popular, meaning it has additional sites of tutorials and people discussing use of that project, so a foundational model ends up knowing quite a bit, if one knows how to construct the context with that information.

This is, of course, tricky with hallucination, but that can be minimized. Which is also why we will all become aware of AI context management if we continue writing software that incorporates AIs. I expect context management is what was meant by prompt engineering. Communicating within engineering disciplines has always been difficult.

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

#456

Post by tudorizer »

diggan wrote: post #445
tudorizer wrote: post #423

Earlier quoted context omitted.

I watched the entire talk, quite carefully. He explicitly states how excited he was about his tweet mentioning English. The disclaimer you mention was indeed mentioned, although it's "in one ear, out the other" with most of his audience. If I give you a glazed donut with a brief asterisk about how sugar can cause diabetes will it stop you from eating the donut? You also expect deterministic outcomes when making analo…

I think this is the moment you're referring to? https://youtu.be/LCEmiRjPEtQ?si=QWkimLapX6oIqAjI&t=236 > maybe you've seen a lot of GitHub code is not just like code anymore there's a bunch of like English interspersed with code and so I think kind of there's a growing category of new kind of code so not only is it a new programming paradigm it's also remarkable to me that it's in our native language of English and s…

> Did you talk with them? Otherwise this is just creating an imaginary argument against some people you just assume they didn't listen.

I have, unfortunately. Start-up founders, managers, investors who taunt the need for engineers because "AI can fix it".

Don't get me wrong, there are plenty of "stochastic parrot" engineers even without AI, but still, not enough to make blanket statements.

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

#457

Post by tudorizer »

diggan wrote: post #450
fifilura wrote: post #439

Earlier quoted context omitted.

Either way, I am not sure it is a requirement on HN to read/view the source. Particularly not a 40min video. Maybe it is tongue-in-cheek, maybe I am serious. I am not sure myself. But sometimes the interesting discussions comes from what is on top of the posters mind when viewing the title. Is that bad?

> Is that bad? It doesn't have to be. But it does get somewhat boring and trite after a while when you start noticing that certain subjects on HN tend to attract general and/or samey comments about $thing, rather than the submission topic within $thing, and I do think that is against the guidelines. > Please don't post shallow dismissals [...] Avoid generic tangents. Omit internet tropes. [...] The specific part of:…

Might sound like a generic tangent, but it's the conclusion people will leave from the talk.

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

#458

Post by tudorizer »

belter wrote: post #449
tudorizer wrote: post #405

95% terrible expression of the landscape, 5% neatly dumbed down analogies. English is a terrible language for deterministic outcomes in complex/complicated systems. Vibe coders won't understand this until they are 2 years into building the thing. LLMs have their merits and he sometimes aludes to them, although it almost feels accidental. Also, you don't spend years studying computer science to learn the language/synt…

You just described Software 4.0...

Can we have it now and skip 3.0?

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

#459

Post by swyx »

karpathy wrote: post #22
gchamonlive wrote: post #2

I think it's interesting to juxtapose traditional coding, neural network weights and prompts because in many areas -- like the example of the self driving module having code being replaced by neural networks tuned to the target dataset representing the domain -- this will be quite useful. However I think it's important to make it clear that given the hardware constraints of many environments the applicability of what…

I kind of say it in words (agreeing with you) but I agree the versioning is a bit confusing analogy because it usually additionally implies some kind of improvement. When I’m just trying to distinguish them as very different software categories.

no no, it actually is a good analogy in 2 ways:

1) it is a breaking change from the prior version

2) it is an improvement in that, in its ideal/ultimate form, it is a full superset of capabilities of the previous version

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

#460

Post by diggan »

mkleczek wrote: post #453
kordlessagain wrote: post #414

Earlier quoted context omitted.

This thread perfectly captures what Karpathy was getting at. We're witnessing a fundamental shift where the interface to computing is changing from formal syntax to natural language. But you can see people struggling to let go of the formal foundations they've built their careers on.

This is why I call all this AI stuff BS. Using a formal language is a feature, not a bug. It is a cornerstone of all human engineering and scientific activity and is the _reason_ why these disciplines are successful. What you are describing (ie. ditching formal and using natural language) is moving humanity back towards magical thinking, shamanism and witchcraft.

> is the _reason_ why these disciplines

Would you say that ML isn't a successful discipline? ML is basically balancing between "formal language" (papers/algorithms) and "non-deterministic outcomes" (weights/inference) yet it seems useful in a wide range of applications, even if you don't think about LLMs at all.

> towards magical thinking, shamanism and witchcraft.

I kind of feel like if you want to make a point about how something is bullshit, you probably don't want to call it "magical thinking, shamanism and witchcraft" because no matter how good your point is, if you end up basically re-inventing the witch hunt, how is what you say not bullshit, just in the other way?

Post reply on HN