Andrej Karpathy: Software Is Changing (Again)

I've done a vibe coding hobby project where I simply give AI instructions on what I want, using a persona-based approach for the agent to generate or fix the code. It worked out pretty well. Who knows how the software engineering landscape will change in 10 to 20 years? I enjoyed Andrej Karpathy's talk about software in the era of AI. ▶ this video

Yes definitely, but I'm pretty sure that he was just saying vibe coding is POSSIBLE and a fun thing to try, to see how far you can get (which is true, it can do some surprising things) Not that companies should literally try to "vibe code" production software Two publishers and three authors fail to understand what “vibe coding” means - link ( I think Karpathy addressed what he meant in this video, though I forget the details: Software Is Changing (Again) ▶ this video ) The phrase got totally taken out of context, probably because it's what people WANTED to believe. They wanted to believe that the hard thing was now easy, and they could make/save a lot of money that way

Ah, I probably should have listed some of the "assumptions" I'm developing it on top of: 1) Regarding the "generation is how learning occurs" claim, I'm going off of this: link Granted, that article refers to retrieval specifically being one major way we learn, and of course learning incorporates many dimensions. But it seems a bit self-evident that retrieval occurs heavily during active problem solving (ie "generation"), and less so during passive learning (ie: just reading/consuming info). From personal experience, I always noticed I learned much more by doing than by consuming documentation alone. But yes, I admit this assumption and my own personal experience/bias is doing a lot of heavy lifting for me... 2) Regarding the "optimal AI productivity process" (AI Generates > Human Validates > Loop) I'm using Karpathy's productivity loop described in his AI startup school talk last month here: ▶ this video Does this help make it more concrete Swyx (name dropping you here since I'm pretty sure you've got a social listener set for your handle ;)? Love to hear your thoughts straight from the hip based on your own personal experiences. Full disclosure: I'm not trying to get too academic about this. In all honestly I'm really trying to get to an informal theory that's useful and practical enough that it can be turned into a regular business process for rapid professional development.

>> A recurring theme presented, however, is that LLM's are somehow not controlled by the corporations which expose them as a service. The presenter made certain to identify three interested actors (governments, corporations, "regular people") and how LLM offerings are not controlled by governments. This is a bit disingenuous. > I don't think that's what he said, he was identifying the first customers and uses. The portion of the presentation I am referencing starts at or near 12:50[0]. Here is what was said: I wrote about this one particular property that strikes me as very different this time around. It's that LLM's like flip they flip the direction of technology diffusion that is usually present in technology. So for example with electricity, cryptography, computing, flight, internet, GPS, lots of new transformative that have not been around. Typically it is the government and corporations that are the first users because it's new expensive etc. and it only later diffuses to consumer. But I feel like LLM's are kind of like flipped around. So maybe with early computers it was all about ballistics and military use, but with LLM's it's all about how do you boil an egg or something like that. This is certainly like a lot of my use. And so it's really fascinating to me that we have a new magical computer it's like helping me boil an egg. It's not helping the government do something really crazy like some military ballistics or some special technology. Note the identification of

Painful to watch. The new tech generation deserves better than hyped presentations from tech evangelists. This reminds me of the Three Amigos and Grady Booch evangelizing the future of software while ignoring the terrible output from Rational Software and the Unified Process. At least we got acknowledgment that self-driving remains unsolved: ▶ this video And Waymo still requires extensive human intervention. Given Tesla's robotaxi timeline, this should crash their stock valuation...but likely won't. You can't discuss "vibe coding" without addressing security implications of the produced artifacts, or the fact that you're building on potentially stolen code, books, and copyrighted training data. And what exactly is Software 3.0? It was mentioned early then lost in discussions about making content "easier for agents."

What is this "clerk" library he used at this timestamp to tell him what to do? ▶ this video Gemini found it via screenshot or context: link This is what he used for login on MenuGen: link

I think this is the moment you're referring to? ▶ this video > 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 so when this blew my mind a few uh I guess years ago now I tweeted this and um I think it captured the attention of a lot of people and this is my currently pinned tweet uh is that remarkably we're now programming computers in English now I agree that it's remarkable that you can tell a computer "What is the biggest city in Maresme?" and it tries to answer that question. I don't think he's saying "English is the best language to make complicated systems uncomplicated with", or anything to that effect. Just like I still think "Wow, this thing is fucking flying" every time I sit onboard a airplane, LLMs are kind of incredible in some ways, yet so "dumb" in some other ways. It sounds to me like he's sharing a similar sentiment but about LLMs. > although it's "in one ear, out the other" with most of his audience. Did you talk with them? Otherwise this is just creating an imaginary argument against some people you just assume they didn't listen. > 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? If I wanted to eat a donut at that point, I g

> Being asked if I'm kidding by the person comparing Google glasses to machine learning algorithms is pretty funny ngl. I didn't draw the comparison. Karpathy, one of the most prominent LLM proponents on the planet -- the guy who invented the term 'vibe-coding' -- drew the comparison.[1] > And the "I don't use these tools and never will" sentiment is rampant in the tech community right now. So yes, I am serious. I think you misunderstood my comment -- or my comment just wasn't clear enough: I quoted the line "It does amaze me that the people who don't use these tools seem to have the most to say about them." and then I asked "You're kidding, right?" In other words, "you can't seriously believe that the nay-sayers 'always have the most to say.'" It's a ridiculous claim. Just about every naysayer 'think piece' -- whether or not it's garbage -- is responding to an overwhelming tidal wave of pro-LLM commentary and press coverage. > Youre not talking about the blog post that completely ignored agentless uses are you? The one that came to the conclusion LLMs arent useful despite only using a subset of its features? I'm referring to this one[2]. It's awful, smug, self-important, sanctimonious nonsense. [1] ▶ this video [2] link