← All source episodes Machine Learning Street Talk / episode intelligence
"Vibe Coding is a Slot Machine" - Jeremy Howard
3 Mar 2026 24 published claims 2 attributable people
Speakers in the public record
Claim mix
belief 9recommendation 5evaluation 4prediction 2commitment 2preference 1observation 1
Evidence policy
Every row below preserves an exact excerpt. Identified speakers are linked; unresolved voices are labeled and excluded from people counts.
Claim ledger
The useful parts, with receipts.
24 published records
“You know, and because deep learning models are universal learning machines, you know, and we had a universal way to train them, I figured if if we get the data right and if the hardware is good enough, then in theory, we ought to be able to build that next word predicting machine, which ought to implicitly build a hierarchical structural understanding of the things that are being described by the text that it is learning to predict?”
- Publisher
- Machine Learning Street Talk
“Yeah. Because the discriminative learning rate thing is interesting because I I think the received wisdom at the time was when you fine tune a model, if the learning rate is too high, you kind of blow out the representations.”
- Publisher
- Machine Learning Street Talk
“It's about, like, creating an environment where humans can grow and engage and share. It's like for me, when I use Solveit, it's the opposite of that experience you described with Claude Code.”
- Publisher
- Machine Learning Street Talk
“I think in the end like IPykernel, I'm finding for example, it's just too big a piece, right? Because in the end, the the team that made the original IPykernel were not able to create a set of tests that correctly exercised it, and therefore real world downstream projects, including the original nb classic, you know, which is what IPykernel was extracted from, didn't work anymore.”
- Publisher
- Machine Learning Street Talk
“I find nearly everything that I expect to work almost always works first time, because I spend a lot of time building up those intuitions, that kind of understanding of how gradients behave.”
- Publisher
- Machine Learning Street Talk
“Work, which I think clearly has been shown to be wrong at many levels at this point.”
- Publisher
- Machine Learning Street Talk
“I think that the thing that you're pointing to here is there's something magic about having an interactive, stateful environment that gives you feedback.”
- Publisher
- Machine Learning Street Talk
“I I think there's a dichotomy though between continual learning, which is when we want to keep training the thing but maintain generality, versus fine tuning a thing to do something specific.”
- Publisher
- Machine Learning Street Talk
“If there are risks with the current state of technology, I mean, I think some of them are the ones we've discussed, which is people enfeebling themselves by basically losing their ability to be to become more competent over time.”
- Publisher
- Machine Learning Street Talk
“I mean, first of all, I I think we shouldn't underestimate the size of how big this combinatorial creativity is.”
- Publisher
- Machine Learning Street Talk
“You know, I'm so torn on this because I agree with you. And I'm also skeptical of people who say that organizations, they they they converge onto ways of doing things, they no longer need to evolve.”
- Publisher
- Machine Learning Street Talk
“I know a domain really well and I can specify it with exquisite detail and I tell Claude code, go and do this thing and the models in my mind doesn't matter.”
- Publisher
- Machine Learning Street Talk
“I think the punch line of this conversation is, and I'm sure you would agree of this, that we need to have the combination of AI and humans working together.”
- Publisher
- Machine Learning Street Talk
“Elon Musk said something a bit similar a few days ago, saying like, oh, LLMs will just spit out the machine code directly. We won't need libraries, programming languages.”
- Publisher
- Machine Learning Street Talk
“The difference between pretending to be intelligent and actually being intelligent is entirely unimportant, as long as you're in the region in which the pretense is actually effective, you know. So so it's actually fine for a great many tasks that LLMs only pretend to be intelligent, because for all intents and purposes, it it it just doesn't matter until you get to the point where it can't pretend anymore.”
- Publisher
- Machine Learning Street Talk
“I basically never have to use a debugger, because I basically never have bugs. And it's not because I'm a particularly good programmer, it's because I build things up small little steps, and each step works and I can see it working and I can interact with it.”
- Publisher
- Machine Learning Street Talk
“I'm a huge fan of taking a model that's incredibly flexible, and then making it more constrained, not by decreasing the size of architecture, but by adding regularization.”
- Publisher
- Machine Learning Street Talk
“They're really bad at software engineering. And then I think that's possibly always gonna be true, because, you know, we're we're asking them to often move outside of their training data, you know, if we're trying to build something that literally hasn't been built before and do it in a better way than has been done before, we're saying, like, don't just copy what was in the training data.”
- Publisher
- Machine Learning Street Talk
“I'm doing things that haven't been done before. And there's this weird thing, I don't know if you've ever seen it before, I see it but I see it multiple times every day, where the LM goes from being incredibly clever to like worse than stupid, like like not understanding the most basic fundamental premises about how the world works.”
- Publisher
- Machine Learning Street Talk
“The thing is, I agree with you that you you can use them in this in this workflow.”
- Publisher
- Machine Learning Street Talk
“And I think and I agree there is a dichotomy there. And I think that dichotomy is a real shame because I think software development is being done wrong.”
- Publisher
- Machine Learning Street Talk
“during my PhD, I used Mathematica and MATLAB”
- Publisher
- Machine Learning Street Talk
“It's like for me, when I use Solveit, it's the opposite of that experience you described with Claude Code. After a couple of hours, I feel energized and happy and fulfilled.”
- Publisher
- Machine Learning Street Talk
“And I really noticed this that I used Anki, and because it was always scheduling my cards just before I was about to forget them, it was always incredibly hard work.”
- Publisher
- Machine Learning Street Talk