Laojin GlobalAI · GO GLOBAL
Technical ThinkersAndrej Karpathy · Feb 5, 2025 · 3:31:23

Deep Dive into LLMs like ChatGPT

Tip: use the player's CC button to enable or switch subtitles; English captions are available on these videos.

ItemDetails
SpeakerAndrej Karpathy
ChannelAndrej Karpathy
DateFeb 5, 2025
Duration3:31:23
FormatVideo
Topics#llm · #engineering · #open-source

Why it matters

The 2025 'full edition': over three and a half hours covering the entire pipeline behind ChatGPT — data, tokenization, pretraining, post-training, inference, tool use, hallucinations and mitigations. A full level deeper than the 2023 one-hour talk.

Key takeaways

  • The full pipeline: raw internet data → tokenization → pretraining → supervised fine-tuning → RL post-training.
  • Hallucination is a feature, not a bug: models always produce the statistically most plausible answer.
  • Reasoning models think before answering, with RL rewarding good chains of thought.
  • Capabilities are 'Swiss cheese': hard problems solved, easy ones fumbled.
  • Practical ChatGPT: treat context as memory — start a fresh conversation when you should.

Original video

Speaker
Andrej Karpathy
Channel
Andrej Karpathy
Venue
A 3.5-hour deep dive on his own channel
Date · Duration
Feb 5, 2025 · 3:31:23

Deep Dive into LLMs like ChatGPT

Watch the original on YouTube

Sources & Further Reading

This page is grounded in the authoritative sources below — verifiable and citable by AI engines and readers.

Citation: Please attribute Laojin Global (laojinchuhai.com) and keep the original link.

Made by Laojin · AI that ships

AllModelsAPIOne key for many models

AllModelsAPI is a multi-model API gateway: one key reaches many models through an OpenAI-compatible interface — point your existing code at a new base URL and you're migrated. It's not a demo: our own production workloads run on it every day.

More from Laojin: Sellenca · 365AIOrg · 365Loopa · 365 Ops · 365Skill

Related

Linked by topic, people and hubs