[1hr Talk] Intro to Large Language Models

Adolf Goebbels
Published on Nov 23, 2023
This is a 1 hour general-audience introduction to Large Language Models: the core technical component behind systems like ChatGPT, Claude, and Bard. What they are, where they are headed, comparisons and analogies to present-day operating systems, and some of the security-related challenges of this new computing paradigm.
As of November 2023 (this field moves fast!).

Context: This video is based on the slides of a talk I gave recently at the AI Security Summit. The talk was not recorded but a lot of people came to me after and told me they liked it. Seeing as I had already put in one long weekend of work to make the slides, I decided to just tune them a bit, record this round 2 of the talk and upload it here on YouTube. Pardon the random background, that's my hotel room during the thanksgiving break.

- Slides as PDF: https://drive.google.com/file/d/1pxx_ZI7O-Nwl7ZLNk5hI3WzAsTLwvNU7/view?usp=share_link (42MB)
- Slides. as Keynote: https://drive.google.com/file/d/1FPUpFMiCkMRKPFjhi9MAhby68MHVqe8u/view?usp=share_link (140MB)

Chapters:
Part 1: LLMs
00:00:00 Intro: Large Language Model (LLM) talk
00:00:20 LLM Inference
00:04:17 LLM Training
00:08:58 LLM dreams
00:11:22 How do they work?
00:14:14 Finetuning into an Assistant
00:17:52 Summary so far
00:21:05 Appendix: Comparisons, Labeling docs, RLHF, Synthetic data, Leaderboard
Part 2: Future of LLMs
00:25:43 LLM Scaling Laws
00:27:43 Tool Use (Browser, Calculator, Interpreter, DALL-E)
00:33:32 Multimodality (Vision, Audio)
00:35:00 Thinking, System 1/2
00:38:02 Self-improvement, LLM AlphaGo
00:40:45 LLM Customization, GPTs store
00:42:15 LLM OS
Part 3: LLM Security
00:45:43 LLM Security Intro
00:46:14 Jailbreaks
00:51:30 Prompt Injection
00:56:23 Data poisoning
00:58:37 LLM Security conclusions
End
00:59:23 Outro

Share Video

  • 560 x 315
  • 640 x 360
  • 853 x 480
  • 1280 x 720

Add to

Flag Video

Rate video

Rate video

DISCLAIMER

The content presented in this stream and/or video may be satirical in nature for entertainment purposes. It may contain realistic scenarios that may include themes of racism, anti-semitism, anti-LGBT sentiment and even elements such as death threats, all purely in the context of parody. In addition, this content may depict or refer to acts of violence in a satirical manner. Shock factor is a common and deliberate element used in these displays to emphasise the satirical message. By continuing to view this content, you acknowledge that you understand the satirical nature of this content, including the depiction of violence and the use of shock factor, and agree that you will not use or interpret this content outside of its intended context. Please remember that humour and satire are complex; they are not intended to belittle or demean, but to engage and challenge social norms through exaggeration. If you have any concerns about content, please feel free to engage in constructive dialogue or report issues to GTV staff.

Up next