hackertube.io

[1hr Talk] Intro to Large Language Models

Andrej Karpathy · talk · Watch on YouTube

LLMs & generative AIMachine learning & deep learning

What it is

Andrej Karpathy gives a one-hour general-audience introduction to large language models, covering what they are, how they are trained, comparisons to operating systems, and security challenges such as jailbreaks.

Why Hacker News recommends it

HN recommends it as the dense, approachable starting point for understanding LLMs and often cites it for specific claims about scaling and training.

  • 9 people recommended it
  • 6 different months
  • 3 strong recommendations
  • first 2023, last 2026

What HN commenters said

  1. “an amazing high-level overview of LLMs, including extensive discussion about attack vectors”

    High-level LLM overview with extensive discussion of attack vectors.

    shrimpx, 2023-11 · Strong recommendation · in “Generative AI for Beginners”

  2. “I highly recommended watching Andrej Karpathy's Intro to LLMs talk”

    Covers System 1 vs System 2 thinking in LLMs.

    FlyingAvatar, 2024-02 · Strong recommendation · in “Ask HN: Do LLMs get "better" with more processing power and or time per request?”

  3. “Start with his short intro to LLMs, only 1 hour long but is dense with valuable stuff”

    Short, dense one-hour intro to LLMs.

    mindwok, 2024-06 · Strong recommendation · in “Why has LLM progress seemingly stalled around the GPT-4 level? Or has it?”

  4. “the recent 1h "busy persons intro" by Andrei Karpathy is great + dense as well”

    Dense one-hour busy person's intro to LLMs.

    jpdus, 2023-12 · Recommendation · in “Ask HN: AI/ML papers to catch up with current state of AI?”

  5. “Anything from Karpathy on youtube”

    Karpathy content suited for listening away from the computer.

    kozikow, 2023-12 · Recommendation · in “Ask HN: AI/ML papers to catch up with current state of AI?”

  6. “Look into the training process -”

    Explains the pretraining and tuning stages of LLM training.

    sk11001, 2024-04 · Recommendation · in “Ask HN: Why has ChatGPT a bias towards correctness?”

  7. “Karpathy has an approachable communication style.”

    Approachable one-hour intro to LLMs.

    runjake, 2024-04 · Recommendation · in “Ask HN: 16 yo Nephew, in E. Africa, wants to train an LLM with on disk Wikipedia”

  8. “I suspect these videos would be higher quality than most offerings from universities or business schools”

    Practitioner-led LLM intro, better than university offerings.

    tikkun, 2024-04 · Recommendation · in “Ask HN: AI Training for Executive Level”

Excerpts from Hacker News comments, linked to the originals. Summaries and labels were written by a language model from those comments.

Topics: llm, pretraining, scaling, jailbreaks, karpathy, system 2

Also recommended by the same people