I just watched this talk by Andrej Karpathy, “Intro to Large Language Models”. Large Language Models (or LLMs) being the AI systems that power tools like ChatGPT.
I’m not neccesarily a stranger to LLMs. I’ve been exposed to the barage of AI news and watched a few small talks on them. I use tools like GitHub Copilpot and ChatGPT daily and I’ve even started building some toy/proof-of-concept projects with them (If intersted, see1 these2 links3)
That said, I’m by no means an expert. This talk served as a good all-around intro and seems to cover a lot of foundational content I’ve not found covered elsewhere (at least not in a format that stuck with me).
Watching the talk brings me back to interesting lectures from excited profs back during my CompSci program. if you’re into that, or just want to learn about how LLMs work, I would recommend giving it a watch!