I’m non-technical but want to deeply understand AI. Andrej Karpathy’s “Intro to LLMs” is the best resource I’ve found so far. Here are my biggest takeaways from his 60-minute talk: 1. An LLM is… | Alex Lieberman
💻 Andrej Karpathy's "Intro to LLMs" highlights: LLMs consist of two files—a large weight file and a small run file—and are more like biological entities than engineered machines. LLaMA-2-70B required thousands of GPUs and millions of dollars; top models scale this 10×. Running models is cheap; training is costly. Open models offer customization, while closed models provide power. Scaling laws drive the GPU and data rush, with novel security risks emerging as LLMs evolve.
Share