HackerTube.dev

State of GPT | BRK216HFS

Microsoft Developer · 785.8K views · 2023-05-25 · 42:40

Open on YouTube ↗

If playback is restricted in your region, try opening the original video. Use Mark watched to add it to your marked videos.

Overview

Andrej Karpathy walks through how GPT assistants are trained, from tokenization and pretraining to supervised finetuning and RLHF, and gives practical prompting strategies and a view of the tooling ecosystem.

On Hacker News

Recommended as the clearest overview of how LLM assistants are built and how to use them well.

Recommended by 6 HN people across 3 months · HN mentions 2023–2025

Topics

LLMs & generative AIMachine learning & deep learning
Search by tags
llmrlhfpromptingkarpathyfine-tuning

What people said

sagarpatil · 2023-06 · Strong recommendation

I would highly recommend watching - State of GPT video by Karpathy at Microsoft Build to get an idea of how LLM’s work. There are some really good prompting ideas. It changed the way I use GPT-4. Video: [VIDEO]

Read the original HN comment ↗
tintor · 2025-02 · Recommendation

Thanks. Here is presentation by Karpathy explaining different stages of LLM training. Explains many details in a form suitable for beginners. [VIDEO]

Read the original HN comment ↗
tikkun · 2024-11 · Recommendation

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 - [VIDEO] LLMs by 3b1b - [LINK] 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"

Read the original HN comment ↗

Sources

Video by Microsoft Developer, played through YouTube.

Data and selection notes

HN summaries and labels may contain AI errors. HN dates refer to discussions, not video publication.

HN Library: HackerTube export (2026-10-31) and open-index/hacker-news. Upstream summaries and classifications may contain AI errors.

Views, duration and playback status refresh separately from the published catalog. When an update fails, existing data remains visible.

Selection checks
  • SaaS & AI candidates: Matches the configured criteria
  • Editor-approved picks: Editorial review is required

Rule matches identify candidates. They do not guarantee video quality or financial results.

About the library and its sources