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.
Episodes
Wednesday Dec 06, 2023
Wednesday Dec 06, 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/bakztfuture
Github - https://www.github.com/bakztfuture
Wednesday Nov 22, 2023
Wednesday 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
Monday Oct 30, 2023
Monday Oct 30, 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:
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
Wednesday Oct 04, 2023
Wednesday Oct 04, 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
Tuesday Sep 05, 2023
Tuesday Sep 05, 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
Thursday Jul 27, 2023
Thursday 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
Tuesday Dec 20, 2022
Tuesday 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
Wednesday Dec 14, 2022
Wednesday 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://www.instagram.com/createlab
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
Thursday Sep 22, 2022
Thursday Sep 22, 2022
What could an AI creative tool like DALL-E 2 or Midjourney look like in the next few years?
This video explores the full set of future possibilities upon us!
GPT-X, Diffusion, and our Multimodal Future (Part II) BOOK: https://docs.google.com/document/d/1TeRMqOsGX8kiK_mNiCt4yxO26Yjk6BdM/
Timestamps:
00:00 - Intro
05:02 - Multimodal Model Characteristics
11:26 - Creating a new image
15:56 - Prompt writing capabilities - Prompt Formatting
16:50 - Prompt autocompletion, intelligent suggestions
19:57 - Built in prompt unbundling
21:57 - Configure Recombinants
23:45 - Recombinant blending modes
25:07 - Configure Recombinant Unbundling Details
26:12 - Recombinant Layers & Node based
28:05 - Recombinant Import Bench
29:48 - Natural Language Image editing - refresh individual objects
31:44 - Edit mode - Natural Langauge Edit Prompts
32:37 - Edit prompt realtime feedback
33:05 - Natural language hex color editing support
34:35 - Advanced Natural Language Edit Prompt Changes
35:53 - Edit prompt intensity (UI controls)
36:59 - Multimodal Object Transformations
37:16 - Lighting & Camera Controls
38:00 - Advanced Editing Tools (Fix AI Weirdness and more)
39:27 - Edit images via markup (markup prompt)
40:43 - Logical Variations
43:57 - Realtime Collaboration
44:28 - Recombinant Collaborators
46:06 - Built in Music Player
48:45 - Creative Hyperparameters
49:20 - Text Capabilities - Magic Text
50:52 - Text Capabilities - Magic Text Fill
52:41 - Latent Variation Scrubbing
53:34 - Explore Alternatives
56:34 - Productivity and commercialization
58:06 - Analysis & Feedback
59:16 - Advanced Multimodal Capabilities
1:03:45 - Offline Capabilities
1:11:11 - Advanced Workflow Support
1:11:58 - Closing thoughts
GPT-X, DALL-E, and our Multimodal Future (Part I):
https://www.youtube.com/playlist?list=PLza3gaByGSXjUCtIuv2x9fwkx3K_3CDmw
Links:
DALL-E 2 Unbundling
https://bakztfuture.substack.com/p/dall-e-2-unbundling
DALL-E 2: Recombinant Art & Design
https://bakztfuture.substack.com/p/dall-e-2-recombinant-art-and-design
DALL-E 2 - Unofficial Natural Language Image Editing, Art Critique Survey
https://bakztfuture.substack.com/p/dall-e-2-unofficial-natural-language-b14
Please note I do not represent, have any affiliation with, nor do I speak on behalf of OpenAI.
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
Wednesday Sep 14, 2022
Wednesday Sep 14, 2022
September 2022 - State of the Union Slideshow presentation!
Watch the video of this presentation here:
https://www.youtube.com/watch?v=qYvRsLWpMBs
Links from this episode:
GPT-X, DALL-E, and our Multimodal Future:
https://www.youtube.com/playlist?list=PLza3gaByGSXjUCtIuv2x9fwkx3K_3CDmw
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/
Recombinant art:
https://bakztfuture.substack.com/p/dall-e-2-recombinant-art-and-design
DALL-E 2: Emerging Content Category Breakdown:
https://bakztfuture.substack.com/p/dall-e-2-emerging-content-category
DALL-E 2 - Unofficial Natural Language Image Editing, Art Critique Survey
https://bakztfuture.substack.com/p/dall-e-2-unofficial-natural-language-b14
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