Multimodal by Bakz T. Future

Bakz T. Future

Multimodal is a podcast about all things GPT-3, DALL-E, and multimodal AI models. Exploring the intersection of AI, creativity, and technology. Hosted by YouTube Creator Bakz T. Future.

  1. 12/06/2023

    #48 - The Art of Prompt Engineering with Andrew Mayne (ex-OpenAI Creative Apps and Science Communicator)

    Discussing Prompt Engineering and recent OpenAI developments with ex-OpenAI Creative Apps and Scientific Communicator Andrew Mayne   Timestamps: 00:00:00 - Teaser Reel Intro 00:01:01 - Intro / Andrew's background 00:02:49 - What was it like working at OpenAI when you first joined? 00:12:59 - Was Andrew basically one of the earliest Prompt Engineers? 00:14:04 - How Andrew Hacked his way into a tech job at OpenAI 00:17:08 - Parallels between Hollywood and Tech jobs 00:20:58 - Parallels between the world of Magic and working at OpenAI 00:25:00 - What was OpenAI like in the Early Days? 00:30:24 - Why it was hard promoting GPT-3 early on 00:31:00 - How would you describe the current 'instruction age' of prompt design? 00:35:22 - What was GPT-4 like freshly trained? 00:39:00 - Is there anything different about the raw base model without RLHF? 00:42:00 - Optimizations that go into Language models like GPT-4 00:43:30 - What was it like using DALL-E 3 very early on? 00:44:38 - Do you know who came up with the 'armchair in the shape of an avocado' prompt at OpenAI? 00:45:48 - Did you experience 'DALL-E Dreams' as a part of the DALL-E 2 beta? 00:47:16 - How else has prompt design changed? 00:49:27 - How has prompt design changed because of ChatGPT? 00:52:40 - How to get ChatGPT to mimick and emulate personalities better? 00:54:30 - Mimicking Personalities II (How to do Style with ChatGPT) 00:56:40 - Fine Tuning ChatGPT for Mimicking Elon Musk 00:59:44 - How do you get ChatGPT to come up with novel and brilliant ideas? 01:02:40 - How do you get ChatGPt to get away from conventional answers? 01:05:14 - Will we ever get single-shot, real true novelty from LLM's? 01:10:05 - Prompting for ChatGPT Voice Mode 01:12:20 - Possibilities and Prompting for GPT-4 Vision 01:15:45 - GPT-4 Vision Use Cases/Startup Ideas 01:21:37 - Does multimodality make language models better or are the benefits marginal? 01:24:00 - Intuitively, has multimodality improved the world model of LLM's like GPT-4? 01:25:33 - What would it take for ChatGPT to write half of your next book? 01:29:10 - Qualitatively, what would it take to convince you about a book written by AI?  What are the characteristics? 01:31:30 - Could an LLM mimick Andrew Mayne's writing style? 01:37:49 - Jailbreaking ChatGPT 01:41:12 - What's the next era of prompt engineering? 01:45:50 - How have custom instructions changed the game? 01:54:41 - How far do you think we are from asking a model how to make 10 million dollars and getting back a legit answer? 02:01:07 - Part II - Making Money with LLM's 02:11:32 - How do you make a chat bot more reliable and safe? 02:12:12 - How do you get ChatGPT to consistently remember criteria and work within constraints? 02:12:45 - What about DALL-E?  How do you get it to better create within constraints? 02:14:14 - What's your prompt practice like? 02:15:10 - Do you intentionally sit down and practice writing prompts? 02:16:45 - How do you build an intuition around prompt design for an LLM? 02:20:00 - How do you like to iterate on prompts? Do you have a process? 02:21:45 - How do you know when you've hit the ceiling with a prompt? 02:24:00 - How do you know a single line prompt is has room to improve? 02:26:40 - Do you actually need to know OpenAI's training data?  What are some ways to mitigate this? 02:30:40 - What are your thoughts on automated prompt writing/optimization? 02:33:20 - How do you get a job as a prompt engineer?  What makes a top tier prompt engineer different from an everyday user? 02:37:20 - How do you think about scaling laws a prompt engineer? 02:39:00 - Effortless Prompt Design 02:40:52 - What are some research areas that would get you a job at OpenAI? 02:43:30 - The Research Possibilities of Optimization & Inference 02:45:59 - If you had to guess future capabilities of GPT-5 what would they be? 02:50:16 - What are some capabilities that got trained out of GPT-4 for ChatGPT? 02:51:10 - Is there any specific capability you could imagine for GPT-5?  Why is it so hard to predict them? 02:56:06 - Why is it hard to predict future LLM capabilities? (Part II) 02:59:47 - What made you want to leave OpenAI and start your own consulting practice? 03:05:29 - Any remaining advice for creatives, entrepreneurs, prompt engineers? 03:09:25 - Closing   Subscribe to the Multimodal By Bakz T. Future Podcast! Spotify - https://open.spotify.com/show/7qrWSE7ZxFXYe8uoH8NIFV Apple Podcasts - https://podcasts.apple.com/us/podcast/multimodal-by-bakz-t-future/id1564576820 Google Podcasts -  https://podcasts.google.com/feed/aHR0cHM6Ly9mZWVkLnBvZGJlYW4uY29tL2Jha3p0ZnV0dXJlL2ZlZWQueG1s Stitcher - https://www.stitcher.com/show/multimodal-by-bakz-t-future Other Podcast Apps (RSS Link) - https://feed.podbean.com/bakztfuture/feed.xml   Connect with me: YouTube - https://www.youtube.com/bakztfuture Substack Newsletter - https://bakztfuture.substack.com​ Twitter - https://www.twitter.com/bakztfuture​ Instagram - https://www.instagram.com/bakztfuture​ Github - https://www.github.com/bakztfuture

    3h 12m
  2. 12/14/2022

    #41 - ChatGPT In Depth with Abran Maldonado (Official OpenAI Ambassador)

    In this episode, we welcome back Abran Maldonado who is an Official OpenAI Community Ambassador.  We discuss all things ChatGPT, OpenAI, and prompt design. We discuss everything ChatGPT in great detail: How it compares to GPT-3 The public reception of ChatGPT Use cases for ChatGPT How you can use ChatGPT in schools and as a parent Where ChatGPT could be going Staying Relevant, Creating, and Adapting ... and so much more! Timestamps: 00:00 - Intro 04:04 - Abran's Background 12:30 - How did you first hear about ChatGPT? 19:46 - ChatGPT First Impressions 28:00 - How do you think about the OpenAI Ecosystem now? 30:38 - Commercializing with the OpenAI API 37:27 - Public Reception - Cool ChatGPT Use cases 40:48 - Public Reception - Jailbreaking ChatGPT 48:40 - Public Reception - ChatGPT vs. Google Search, learning 55:55 - How do you feel about ChatGPT virality? 01:01:25 - Office Hours with OpenAI Ambassadors 01:02:40 - Staying Relevant with ChatGPT 01:11:20 - ChatGPT Browsing the Web (?) WebGPT 01:16:35 - AI and Safety 01:20:30 - The benefit of ChatGPT browsing the web 01:20:09 - ChatGPT Formatting - ChatGPT encylopedia (?) 01:23:43 - ChatGPT and EDU 01:25:08 - Do you have any advice to teachers and parents? 01:30:08 - Language Models and Education Debate, The Future of Education 01:42:40 - Prompt Engineering is dead, long live dialogue engineering! 01:53:57 - Parallels Between Music Scene and the GPT-3/DALL-E/OpenAI Ecosystem 02:00:10 - Music Industry x AI Models 02:05:33 - How to prepare for upcoming Music AI Models? 02:11:05 - Listener Questions 02:20:06 - Closing Thoughts 02:24:00 - Outro   Abran Maldonado    https://twitter.com/abran https://www.instagram.com/createlab https://createlabs.io/meet-claira   Links from this episode: ChatGPT: https://openai.com/blog/chatgpt/ Is Prompt Design Over? https://bakztfuture.substack.com/p/is-prompt-design-over InstructGPT: https://openai.com/blog/instruction-following/ InstructGPT vs. google search: https://bakztfuture.substack.com/p/instructgpt-google-search WebGPT: https://openai.com/blog/webgpt/ My Biggest 2022 Prediction: GPT-3 will take over schools and college campuses https://bakztfuture.substack.com/p/my-biggest-2022-prediction-gpt-3   Subscribe to the Multimodal Podcast!   Spotify - https://open.spotify.com/show/7qrWSE7ZxFXYe8uoH8NIFV Apple Podcasts - https://podcasts.apple.com/us/podcast/multimodal-by-bakz-t-future/id1564576820 Google Podcasts -  https://podcasts.google.com/feed/aHR0cHM6Ly9mZWVkLnBvZGJlYW4uY29tL2Jha3p0ZnV0dXJlL2ZlZWQueG1s Stitcher - https://www.stitcher.com/show/multimodal-by-bakz-t-future Other Podcast Apps (RSS Link) - https://feed.podbean.com/bakztfuture/feed.xml   Connect with me: YouTube - https://www.youtube.com/bakztfuture Substack Newsletter - https://bakztfuture.substack.com​ Twitter - https://www.twitter.com/bakztfuture​ Instagram - https://www.instagram.com/bakztfuture​ Github - https://www.github.com/bakztfuture​

    2h 25m

Ratings & Reviews

4.1
out of 5
7 Ratings

About

Multimodal is a podcast about all things GPT-3, DALL-E, and multimodal AI models. Exploring the intersection of AI, creativity, and technology. Hosted by YouTube Creator Bakz T. Future.