Episodes

  • #48 - The Art of Prompt Engineering with Andrew Mayne (ex-OpenAI Creative Apps and Science Communicator)
    Dec 6 2023
    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/...
    Show more Show less
    3 hrs and 12 mins
  • #47 - Message to OpenAI [The Return of Sam Altman as CEO of OpenAI]
    Nov 22 2023

    Sam and Greg back are at OpenAI - here's my message to them

    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

    Show more Show less
    7 mins
  • #46 - AI Safety with Wyatt Tessari L’allié and Mario Gibney (AIGS Canada)
    Oct 31 2023

    Exploring AI Safety in Canada, how politics works, learning more about the AIGS Canada non profit.

    (Video version on YouTube channel coming soon)

    AIGS Policy whitepaper:

    https://aigs.ca/advocacy/

    AIGS Canada: https://aigs.ca/

    Mario Gibney:

    https://twitter.com/Mario_Gibney

    https://www.linkedin.com/in/mario-gibney-08bb7b45/

    Wyatt Tessari L’allié:

    https://twitter.com/WyattTessari

    https://www.linkedin.com/in/wyatttessari/

    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

    Show more Show less
    2 hrs and 3 mins
  • #45 - BREAKING: DALL-E 3 First Impressions (Official ChatGPT Plugin)
    Oct 4 2023

    My first impressions getting access to the exclusive DALL-E 3 release as an Official ChatGPT plugin. So far, I'm pretty impressed.

    Tweet thread unboxing and exploring DALL-E 3:

    https://twitter.com/bakztfuture/status/1709303961625264572

    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

    Show more Show less
    11 mins
  • #44 - Goodbye DALL-E (Complete Tell-All)
    Sep 5 2023

    Why I am no longer optimistic about DALL-E ...

    Goodbye DALL-E

    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

    Show more Show less
    38 mins
  • #43 - 2023 and Superalignment
    Jul 27 2023

    Multimodal Returns!

    Topics I've covered:

    • Personal life updates
    • 2023 - the era we're in
    • The Highs and Lows of AI Media
    • OpenAI Superalignment Announcements

    Timestamps: [coming soon]

    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​

    Show more Show less
    45 mins
  • #42- ChatGPT/DALL-E 2022 Year in Review, How to Start a Startup with David Shapiro
    Dec 20 2022

    Reviewing major events from the 2022 year with returning guest David Shapiro!

    Timestamps: 00:00 Intro 04:58 #7 - Nvidia NeMo Megatron 15:00 #6 - Petals 23:24 #5 - Bloom 28:25 #4 - Meta AI wins at Diplomacy 41:18 #3 - Crypto crash! FTX implosion 56:54 #2- DALL-E 2, Midjourney, Stable Diffusion 1:18:29 #1- ChatGPT 1:29:41 Honourable Mentions 1:56:01 How to Start a Startup Presentation 2:26:37 Post Presentation Discussion 3:09:45 Outro

    David Shapiro: https://www.youtube.com/c/DavidShapiroAutomator https://www.patreon.com/daveshap https://www.davidkshapiro.com/ https://twitter.com/dshap_automator

    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​

    Show more Show less
    3 hrs and 11 mins
  • #41 - ChatGPT In Depth with Abran Maldonado (Official OpenAI Ambassador)
    Dec 14 2022

    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​

    Show more Show less
    2 hrs and 25 mins