Practical AI

Practical AI

By Daniel Whitenack and Chris BensonTechnology
Download on the App Store
  • Favorites

    316

    Followers

  • Latest release

    3 days ago

  • Typical duration

    47 min

    per episode

Based on Podcast App listening data

All Practical AI episodes

  • Large models on CPUs

    Model sizes are crazy these days with billions and billions of parameters. As Mark Kurtz explains in this episode, this makes inference slow and expensive despite the fact that up to 90%+ of the parameters don’t influence the outputs at all.

    Mark helps us understand all of the practicalities and progress that is being made in model optimization and CPU inference, including the increasing opportunities to run LLMs and other Generative AI models on commodity hardware.


    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:

    • Mark Kurtz – LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • Neural Magic
    • SparseML
    • SparseZoo
    • Neural Magic Scales up MLPerf™ Inference v3.0 Performance With Demonstrated Power Efficiency; No GPUs Needed
    • Deploy Optimized Hugging Face Models With DeepSparse and SparseZoo
    • SparseGPT: Remove 100 Billion Parameters for Free

    Upcoming Events: 

    • Register for upcoming webinars here!
    39 min
  • Causal inference

    With all the LLM hype, it’s worth remembering that enterprise stakeholders want answers to “why” questions. Enter causal inference. Paul Hünermund has been doing research and writing on this topic for some time and joins us to introduce the topic. He also shares some relevant trends and some tips for getting started with methods including double machine learning, experimentation, difference-in-difference, and more.

    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 News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 

    Featuring:

    • Paul Hünermund – Website, LinkedIn, X
    • Chris Benson – Website, GitHub, LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • How Can Causal Machine Learning Improve Business Decisions?
    • Causal Inference is More than Fitting the Data Well
    • Causal Data Science in Practice
    • Causal Discovery
    • DoWhy Github
    • The Book of Why
    • Causal Data Science Meeting
    • Paul’s study on causal ML adoption in industry (incl. an overview of useful software packages in Table 3)
    • Causal Data Science MOOC on Udemy

    Upcoming Events: 

    • Register for upcoming webinars here!
    43 min
  • Capabilities of LLMs 🤯

    Large Language Model (LLM) capabilities have reached new heights and are nothing short of mind-blowing! However, with so many advancements happening at once, it can be overwhelming to keep up with all the latest developments. To help us navigate through this complex terrain, we’ve invited Raj - one of the most adept at explaining State-of-the-Art (SOTA) AI in practical terms - to join us on the podcast.

    Raj discusses several intriguing topics such as in-context learning, reasoning, LLM options, and related tooling. But that’s not all! We also hear from Raj about the rapidly growing data science and AI community on TikTok.


    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:

    • Rajiv Shah – Website, GitHub, LinkedIn, X
    • Chris Benson – Website, GitHub, LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • Solving AI Tasks with ChatGPT and its Friends in HuggingFace | GitHub
    • Generative Agents: Interactive Simulacra of Human Behavior
    • Wolfram ChatGPT
    • Comparing LLMs
    • LangChain
    • Learn about LLMs: 
      • Emergence and reasoning in large language models (Jason Wei)
      • Sparks of Artificial General Intelligence
    • Learning Prompting
    • Getting Started with Transformers: 
      • Transformers course (free)
      • Tasks at Hugging Face
    • Training your own LLM Models: 
      • Efficient Large Language Model training with LoRA and Hugging Face
      • PEFT (Parameter-Efficient Fine-Tuning)
    • Dolly blog post
    • Illustrating Reinforcement Learning from Human Feedback

    Upcoming Events: 

    • Register for upcoming webinars here!
    39 min
  • Computer scientists as rogue art historians

    What can art historians and computer scientists learn from one another? Actually, a lot! Amanda Wasielewski joins us to talk about how she discovered that computer scientists working on computer vision were actually acting like rogue art historians and how art historians have found machine learning to be a valuable tool for research, fraud detection, and cataloguing. We also discuss the rise of generative AI and how we this technology might cause us to ask new questions like: “What makes a photograph a photograph?”


    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. 
    • Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! 

    Featuring:

    • Amanda Wasielewski – Website, X
    • Chris Benson – Website, GitHub, LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • Computational Formalism Art History and Machine Learning

    Upcoming Events: 

    • Register for upcoming webinars here!
    44 min
  • Accelerated data science with a Kaggle grandmaster

    Daniel and Chris explore the intersection of Kaggle and real-world data science in this illuminating conversation with Christof Henkel, Senior Deep Learning Data Scientist at NVIDIA and Kaggle Grandmaster. Christof offers a very lucid explanation into how participation in Kaggle can positively impact a data scientist’s skill and career aspirations. He also shared some of his insights and approach to maximizing AI productivity uses GPU-accelerated tools like RAPIDS and DALI.


    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:

    • Christof Henkel – GitHub, LinkedIn, X
    • Chris Benson – Website, GitHub, LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • Christof Henkel | Kaggle
    • NVIDIA Kaggle Grandmasters
    • Kaggle
    • NVIDIA RAPIDS
    • NVIDIA Data Loading Library (DALI)

    Upcoming Events: 

    • Register for upcoming webinars here!
    44 min
  • Explainable AI that is accessible for all humans

    We are seeing an explosion of AI apps that are (at their core) a thin UI on top of calls to OpenAI generative models. What risks are associated with this sort of approach to AI integration, and is explainability and accountability something that can be achieved in chat-based assistants?

    Beth Rudden of Bast.ai has been thinking about this topic for some time and has developed an ontological approach to creating conversational AI. We hear more about that approach and related work in this episode.


    Sponsors:

    • 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. 
    • 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
    • Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! 

    Featuring:

    • Beth Rudden – LinkedIn, X
    • Chris Benson – Website, GitHub, LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • Bast.ai

    Upcoming Events: 

    • Register for upcoming webinars here!
    46 min
  • AI search at You.com

    Neural search and chat-based search are all the rage right now. However, You.com has been innovating in these topics long before ChatGPT. In this episode, Bryan McCann from You.com shares insights related to our mental model of Large Language Model (LLM) interactions and practical tips related to integrating LLMs into production systems.


    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:

    • Bryan McCann – GitHub, LinkedIn, X
    • Chris Benson – Website, GitHub, LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • You.com
    • Open Platform for developers
    • Join the You.com Discord server

    Upcoming Events: 

    • Register for upcoming webinars here!
    42 min
  • End-to-end cloud compute for AI/ML

    We’ve all experienced pain moving from local development, to testing, and then on to production. This cycle can be long and tedious, especially as AI models and datasets are integrated. Modal is trying to make this loop of development as seamless as possible for AI practitioners, and their platform is pretty incredible!

    Erik from Modal joins us in this episode to help us understand how we can run or deploy machine learning models, massively parallel compute jobs, task queues, web apps, and much more, without our own infrastructure.


    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:

    • Erik Bernhardsson – Website, GitHub, X
    • Chris Benson – Website, GitHub, LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • Modal
    • Episode 142 discussing Erik’s “building a data team” article

    Upcoming Events: 

    • Register for upcoming webinars here!
    45 min
  • Success (and failure) in prompting

    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.


    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, X
    • Daniel Whitenack – Website, GitHub, X

    Show 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

    Upcoming Events: 

    • Register for upcoming webinars here!
    44 min
  • Applied NLP solutions & AI education

    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.


    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, X
    • Chris Benson – Website, GitHub, LinkedIn, X
    • Daniel Whitenack – Website, GitHub, X

    Show Notes:

    • Jay’s popular blog (with posts including “The Illustrated Transformer”)
    • co:here
    • Topically sandbox - topic modeling
    • co:here’s prompt engineering guide

    Upcoming Events: 

    • Register for upcoming webinars here!
    39 min