Lex Fridman: preference

Transcript context

…Tinygrad is now 2,700 lines and it can run LLaMA and stable diffusion and all of this stuff is in 2,700 lines. Boilerplate and abstraction in directions and all these things are just bad code. Well, let’s talk about good code and bad code. I would say, for generic scripts that I write just offhand, 80% of it is written by GPT, just like quick offhand stuff. So not libraries, not performing code, not stuff for robotics and so on. Just quick stuff because so much of programming is doing some boilerplate, but to do so efficiently and quickly because you can’t really automate it fully with generic method, a generic kind of IDE type of recommendation or something like this. You do need to have some of the complexity of language models. Yeah, I guess if I was really writing, maybe today, if I wrote a lot of data parsing stuff… I don’t play CTFs anymore, but if I still play CTFs, a lot of is just you have to write a parser for this data format or admin of code. I wonder when the models are going to start to help with that code and they may. And the models also may help you with speed and the models are very fast, but where the models won’t, my programming speed is not at all limited by my typing speed. And in very few cases, it is yes. If I’m writing some script to just parse some weird data format, sure, my programming speed is limited by my typing speed.…

Stored transcript either side of the excerpt. The highlighted words are the published quote; the surrounding text is unedited source, never generated.