How I use LLMs

Andrej Karpathy · Advanced ·🧠 Large Language Models ·1y ago

Key Takeaways

Andrej Karpathy demonstrates various Large Language Models (LLMs) and their applications, including ChatGPT, Claude, and NotebookLM, showcasing their capabilities and uses in real-life scenarios.

Original Description

The example-driven, practical walkthrough of Large Language Models and their growing list of related features, as a new entry to my general audience series on LLMs. In this more practical followup, I take you through the many ways I use LLMs in my own life. Chapters 00:00:00 Intro into the growing LLM ecosystem 00:02:54 ChatGPT interaction under the hood 00:13:12 Basic LLM interactions examples 00:18:03 Be aware of the model you're using, pricing tiers 00:22:54 Thinking models and when to use them 00:31:00 Tool use: internet search 00:42:04 Tool use: deep research 00:50:57 File uploads, adding documents to context 00:59:00 Tool use: python interpreter, messiness of the ecosystem 01:04:35 ChatGPT Advanced Data Analysis, figures, plots 01:09:00 Claude Artifacts, apps, diagrams 01:14:02 Cursor: Composer, writing code 01:22:28 Audio (Speech) Input/Output 01:27:37 Advanced Voice Mode aka true audio inside the model 01:37:09 NotebookLM, podcast generation 01:40:20 Image input, OCR 01:47:02 Image output, DALL-E, Ideogram, etc. 01:49:14 Video input, point and talk on app 01:52:23 Video output, Sora, Veo 2, etc etc. 01:53:29 ChatGPT memory, custom instructions 01:58:38 Custom GPTs 02:06:30 Summary Links - Tiktokenizer https://tiktokenizer.vercel.app/ - OpenAI's ChatGPT https://chatgpt.com/ - Anthropic's Claude https://claude.ai/ - Google's Gemini https://gemini.google.com/ - xAI's Grok https://grok.com/ - Perplexity https://www.perplexity.ai/ - Google's NotebookLM https://notebooklm.google.com/ - Cursor https://www.cursor.com/ - Histories of Mysteries AI podcast on Spotify https://open.spotify.com/show/3K4LRyMCP44kBbiOziwJjb - The visualization UI I was using in the video: https://excalidraw.com/ - The specific file of Excalidraw we built up: https://drive.google.com/file/d/1DN3LU3MbKI00udxoS-W5ckCHq99V0Uqs/view?usp=sharing - Discord channel for Eureka Labs and this video: https://discord.gg/3zy8kqD9Cp Educational Use Licensing This video is freely available for educati
Watch on YouTube ↗ (saves to browser)
Sign in to unlock AI tutor explanation · ⚡30

Playlist

Uploads from Andrej Karpathy · Andrej Karpathy · 17 of 17

← Previous Next →

This video provides a practical walkthrough of Large Language Models and their applications, showcasing their capabilities and uses in real-life scenarios. Viewers can learn how to use LLMs for various tasks, such as chat interactions, data analysis, and code composition. The video also covers the importance of understanding the model being used and its pricing tiers.

Key Takeaways
  1. Explore ChatGPT and its capabilities
  2. Understand the importance of model selection and pricing tiers
  3. Use LLMs for basic interactions and data analysis
  4. Utilize LLMs for code composition and generation
  5. Experiment with advanced features, such as audio and image input/output
💡 The key to effectively using LLMs is to understand their capabilities and limitations, as well as the importance of selecting the right model for the task at hand.

Related Reads

Chapters (22)

Intro into the growing LLM ecosystem
2:54 ChatGPT interaction under the hood
13:12 Basic LLM interactions examples
18:03 Be aware of the model you're using, pricing tiers
22:54 Thinking models and when to use them
31:00 Tool use: internet search
42:04 Tool use: deep research
50:57 File uploads, adding documents to context
59:00 Tool use: python interpreter, messiness of the ecosystem
1:04:35 ChatGPT Advanced Data Analysis, figures, plots
1:09:00 Claude Artifacts, apps, diagrams
1:14:02 Cursor: Composer, writing code
1:22:28 Audio (Speech) Input/Output
1:27:37 Advanced Voice Mode aka true audio inside the model
1:37:09 NotebookLM, podcast generation
1:40:20 Image input, OCR
1:47:02 Image output, DALL-E, Ideogram, etc.
1:49:14 Video input, point and talk on app
1:52:23 Video output, Sora, Veo 2, etc etc.
1:53:29 ChatGPT memory, custom instructions
1:58:38 Custom GPTs
2:06:30 Summary
Up next
5 Levels of AI Agents - From Simple LLM Calls to Multi-Agent Systems
Dave Ebbelaar (LLM Eng)
Watch →