With the recent proliferation of generative AI models (from OpenAI, co:here, Anthropic, etc.), practitioners are racing to come up with best practices around prompting, grounding, and control of outputs. Chris and Daniel take a deep dive into the kinds of behavior we are seeing with this latest wave of models (both good and bad) and what leads to that behavior. They also dig into some prompting and integration tips. Join the discussionChangelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!Sponsors:Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with extended episodes, make the ads disappear, and increment your audio quality with higher bitrate mp3s. Let’s do this! Featuring:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Generative AI model behavior in the news: Microsoft’s AI chatbot is going off the rails A Conversation With Bing’s Chatbot Left Me Deeply Unsettled Sydney’s gaslighting ChatGPT political bias Stable Diffusion amplification of stereotypes Useful guides related to prompt engineering: co:here prompt engineering guide Prompt engineering overview from Elvis Savaria 10 Amazing Resources For Prompt Engineering, ChatGPT, and GPT-3 Image generation prompt engineering guides: see here and here Something missing or broken? PRs welcome!

We’re super excited to welcome Jay Alammar to the show. Jay is a well-known AI educator, applied NLP practitioner at co:here, and author of the popular blog, “The Illustrated Transformer.” In this episode, he shares his ideas on creating applied NLP solutions, working with large language models, and creating educational resources for state-of-the-art AI. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Featuring:Jay Alammar – Website, GitHub, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes: Jay’s popular blog (with posts including “The Illustrated Transformer”) co:here Topically sandbox - topic modeling co:here’s prompt engineering guide Something missing or broken? PRs welcome!

We’ve been hearing about “serverless” CPUs for some time, but it’s taken a while to get to serverless GPUs. In this episode, Erik from Banana explains why its taken so long, and he helps us understand how these new workflows are unlocking state-of-the-art AI for application developers. Forget about servers, but don’t forget to listen to this one! Join the discussionChangelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!Sponsors:Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with extended episodes, make the ads disappear, and increment your audio quality with higher bitrate mp3s. Let’s do this! Featuring:Erik Dunteman – Website, GitHub, LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Banana - Scale your machine learning inference and training on serverless GPUs. Something missing or broken? PRs welcome!

Worlds are colliding! This week we join forces with the hosts of the MLOps.Community podcast to discuss all things machine learning operations. We talk about how the recent explosion of foundation models and generative models is influencing the world of MLOps, and we discuss related tooling, workflows, perceptions, etc. Join the discussionChangelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!Sponsors:Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Changelog++ – You love our content and you want to take it to the next level by showing your support. We’ll take you closer to the metal with extended episodes, make the ads disappear, and increment your audio quality with higher bitrate mp3s. Let’s do this! Featuring:Demetrios Brinkmann – XMihail Eric – Website, GitHub, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:MLOps.Community Something missing or broken? PRs welcome!

What’s the current reality and practical implications of using 3D environments for simulation and synthetic data creation? In this episode, we cut right through the hype of the Metaverse, Multiverse, Omniverse, and all the “verses” to understand how 3D assets and tooling are actually helping AI developers develop industrial robots, autonomous vehicles, and more. Beau Perschall is at the center of these innovations in his work with NVIDIA, and there is no one better to help us explore the topic! Join the discussionChangelog++ members save 1 minute on this episode because they made the ads disappear. Join today!Sponsors:Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Featuring:Beau Perschall – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes: NVIDIA’s Omniverse Beau’s GTC 2023 session around how to build simulation-ready USD 3D assets Tech blog around Omniverse and SimReady assets Something missing or broken? PRs welcome!

Creating and sharing reproducible development environments for AI experiments and production systems is a huge pain. You have all sorts of weird dependencies, and then you have to deal with GPUs and NVIDIA drivers on top of all that! brev.dev is attempting to mitigate this pain and create delightful GPU dev environments. Now that sounds practical! Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Sponsors:Fastly – Our bandwidth partner. Fastly powers fast, secure, and scalable digital experiences. Move beyond your content delivery network to their powerful edge cloud platform. Learn more at fastly.com Fly.io – The home of Changelog.com — Deploy your apps and databases close to your users. In minutes you can run your Ruby, Go, Node, Deno, Python, or Elixir app (and databases!) all over the world. No ops required. Learn more at fly.io/changelog and check out the speedrun in their docs. Featuring:Nader Khalil – XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:brev.dev DISCOUNT for our listeners 🔥: Use coupon code “practical-ai-2023” for 5 hours of free GPU compute! brev.dev doesn’t offer credits often, so the credit redemption button is hidden by default. Go to this link to expose the button. Something missing or broken? PRs welcome!

Why is ML is so poorly adopted in small organizations (hint: it’s not because they don’t have enough data)? In this episode, Kirsten Lum from Storytellers shares the patterns she has seen in small orgs that lead to a successful ML practice. We discuss how the job of a ML Engineer/Data Scientist is different in that environment and how end-to-end project management is key to adoption. Join the discussionChangelog++ members save 2 minutes on this episode because they made the ads disappear. Join today!Sponsors:The Changelog – Conversations with the hackers, leaders, and innovators of the software world Featuring:Kirsten Lum – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes: storytellers.ai Trello Something missing or broken? PRs welcome!

Daniel and Chris do a deep dive into OpenAI’s ChatGPT, which is the first LLM to enjoy direct mass adoption by folks outside the AI world. They discuss how it works, its effect on the world, ramifications of its adoption, and what we may expect in the future as these types of models continue to evolve. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Featuring:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes: ChatGPT OpenAI Blog: ChatGPT Illustrating Reinforcement Learning from Human Feedback (RLHF) Something missing or broken? PRs welcome!

While at EMNLP 2022, Daniel got a chance to sit down with an amazing group of researchers creating NLP technology that actually works for their local language communities. Just Zwennicker (Universiteit van Amsterdam) discusses his work on a machine translation system for Sranan Tongo, a creole language that is spoken in Suriname. Andiswa Bukula (SADiLaR), Rooweither Mabuya (SADiLaR), and Bonaventure Dossou (Lanfrica, Mila) discuss their work with Masakhane to strengthen and spur NLP research in African languages, for Africans, by Africans. The group emphasized the need for more linguistically diverse NLP systems that work in scenarios of data scarcity, non-Latin scripts, rich morphology, etc. You don’t want to miss this one! Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Featuring:Just Zwennicker – LinkedInAndiswa Bukula – XRooweither Mabuya – XBonaventure Dossou – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:EMNLP 2022 papers from the guests: Towards a general purpose machine translation system for Sranantongo MasakhaNER 2.0: Africa-centric Transfer Learning for Named Entity Recognition AfroLM: A Self-Active Learning-based Multilingual Pretrained Language Model for 23 African Languages Other links relevant to the discussion: Masakhane Lanfrica The South African Centre for Digital Language Resources (SADiLaR) Something missing or broken? PRs welcome!

José and Ricardo joined Daniel at EMNLP 2022 to discuss state-of-the-art machine translation, the WMT shared tasks, and quality estimation. Among other things, they talk about Unbabel’s innovations in quality estimation including COMET, a neural framework for training multilingual machine translation (MT) evaluation models. Join the discussionChangelog++ members support our work, get closer to the metal, and make the ads disappear. Join today!Featuring:Ricardo Rei – XJosé Souza – XDaniel Whitenack – Website, GitHub, XShow Notes: Unbabel COMET The WMT workshop/ conference EMNLP Something missing or broken? PRs welcome!