hackertube.io

A Hackers' Guide to Language Models

Jeremy Howard · tutorial · Watch on YouTube

LLMs & generative AIMachine learning & deep learning

What it is

Jeremy Howard's 90-minute practical tour of language models. It covers how they work, GPT-4's capabilities and limits, using the OpenAI API, code writing, data analysis and fine-tuning.

Why Hacker News recommends it

Repeatedly named the best practical tutorial for using LLMs, with a well-liked fine-tuning section.

  • 8 people recommended it
  • 8 different months
  • 4 strong recommendations
  • first 2023, last 2024

What HN commenters said

  1. “best LLM usage tutorial I've seen so far”

    Practical LLM usage tutorial including fine-tuning small models.

    tarruda, 2023-09 · Strong recommendation · in “A Hackers' Guide to Language Models [video]”

  2. “Jeremy Howard's amazing guide to language models”

    Tip to erase chat history after GPT makes an error.

    dojitza1, 2023-11 · Strong recommendation · in “Effective GPT-4 Programming”

  3. “jeremy howard also has a fantastic video that is more around how to use LLMs”

    Fantastic video on how to use LLMs.

    mangoman, 2024-02 · Strong recommendation · in “I'm an Old Fart and AI Makes Me Sad”

  4. “but the whole talk is great.”

    Covers fine-tuning with timestamped section; whole talk is good.

    code_biologist, 2023-10 · Recommendation · in “Mistral 7B Paper on ArXiv”

  5. “Jeremy Howard has a great video”

    Limitations and capabilities section on how prompts affect LLM quality.

    lsedgwick, 2023-10 · Recommendation · in “Advent of Code 2023's new AI/LLM Policy”

  6. “thank you for all the amazing free content you've already put out”

    Thanks for Howard's free educational content such as this lecture.

    ghj, 2023-12 · Recommendation · in “A new old kind of R&D lab”

  7. “my favourite guide to fine-tuning is the section of this Jeremy Howard video that shows how to train a text-to-SQL model”

    Section showing how to train a text-to-SQL model.

    simonw, 2024-03 · Recommendation · in “GPT-4, without specialized training, beat a GPT-3.5 class model that cost $10M”

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

    Practitioner-led LLM talk likely better than business school 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: language models, gpt-4, fine-tuning, openai api, jeremy howard, prompting

Also recommended by the same people