Large Language Models explained briefly
Why Hacker News recommends it
HN commenters hand it out as a short, accessible explanation of how LLMs work, both to newcomers asking where to start and as a reference for the next-token-prediction point.
Recommended by 3 people across 3 different months, 2024 to 2026.
What it is
A roughly eight-minute animated primer from 3Blue1Brown on how large language models work, covering chatbots as next-token predictors, pretraining, and the transformer architecture. It was made for an exhibit at the Computer History Museum and links to longer technical lessons.
What people said
Recommends tikkun · 2024-11 · Hacker News · on “Ask HN: Recommendation for a SWE looking to get up to speed with latest on AI”
It sounds like you want more broad stuff, not necessarily learning how to train models. More like learning to use them and how they work. [LINK] and Hacker's Guide to LLMs by Jeremy from Fast.ai - [LINK] State of GPT by Karpathy - [LINK] LLMs by 3b1b - [this video] Visualizing transformers by 3b1b - [LINK] How ChatGPT trained - [LINK] AI in a nutshell - [LINK] How Carlini uses LLMs - [LINK] For staying updated: X/Twitter & Bluesky. Go and follow people that work at OpenAI, Anthropic, Google DeepMind, and xAI. Podcasts: No Priors, Generally Intelligent, Dwarkesh Patel, Sequoia's "Training Data"
Recommends tocs3 · 2025-01 · Hacker News · on “Ask HN: What should I read/watch/code next to understand ChatGPT technicals?”
3Brown1Blue on youtube if chock full of interesting videos. "Large Language Models explained briefly": [this video] Lots of other stuff also.
Recommends ThrowawayR2 · 2026-09 · Hacker News · on “Ask HN: Are we losing our engineering literacy?”
We know that LLMs are token pattern predictors because that's literally how the algorithm works. There have been plenty of explanations by the paper authors and by other sources, e.g. 3blue1brown's summary at [this video] . That LLMs are "glorified autocomplete"(sic) is beyond dispute. The burden is on the LLM promoters to back up their frequent claim that the brain is the same as an LLM and they are abjectly unable to do it. (Maybe they should have their LLMs write the proof for them if they are unable to figure it out themselves? Good luck with that.)