Daniel had the chance to sit down with @swyx and Alessio from the Latent Space pod in SF to talk about current AI trends and to highlight some key learnings from past episodes. The discussion covers open access LLMs, smol models, model controls, prompt engineering, and LLMOps. This mashup is magical. Don’t miss it! 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. Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! Featuring:Shawn Wang – Twitter, GitHub, WebsiteAlessio Fanelli – Twitter, GitHub, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Latent Space podcast Featured Latent Space episodes: Benchmarks Reza Shabani MosaicML and MPT Segment Anything Mike Conover Featured Practical AI episodes: From notebooks to Netflix scale with Metaflow Capabilities of LLMs 🤯 ML at small organizations Prediction Guard Data Dan Something missing or broken? PRs welcome!

Lately.AI has been working for years on content generation systems that capture your unique “voice” and are tailored to your unique audience. At first, they didn’t know that they were going to build an AI system, but now they have a state-of-the-art generative platform that provides much more than “prompting” out of thin air. Lately.AI’s CEO Kate explain their journey, her perspective on generative AI in marketing, and much more in this episode! 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 News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Kate Bradley Chernis – Twitter, LinkedInChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Lately.AI Something missing or broken? PRs welcome!

You can’t build robust systems with inconsistent, unstructured text output from LLMs. Moreover, LLM integrations scare corporate lawyers, finance departments, and security professionals due to hallucinations, cost, lack of compliance (e.g., HIPAA), leaked IP/PII, and “injection” vulnerabilities. In this episode, Chris interviews Daniel about his new company called Prediction Guard, which addresses these issues. They discuss some practical methodologies for getting consistent, structured output from compliant AI systems. These systems, driven by open access models and various kinds of LLM wrappers, can help you delight customers AND navigate the increasing restrictions on “GPT” models. Join the discussionChangelog++ members save 3 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 News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Chris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Prediction Guard Prediction Guard docs LLMs in Production II event Something missing or broken? PRs welcome!

Large Language Models (LLMs) continue to amaze us with their capabilities. However, the utilization of LLMs in production AI applications requires the integration of private data. Join us as we have a captivating conversation with Jerry Liu from LlamaIndex, where he provides valuable insights into the process of data ingestion, indexing, and query specifically tailored for LLM applications. Delving into the topic, we uncover different query patterns and venture beyond the realm of vector databases. 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. Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! Featuring:Jerry Liu – Twitter, GitHubChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: LlamaIndex Docs LlamaHub LlamaIndex Blog Something missing or broken? PRs welcome!

At the recent ODSC East conference, Daniel got a chance to sit down with Erin Mikail Staples to discuss the process of gathering human feedback and creating an instruction tuned Large Language Models (LLM). They also chatted about the importance of open data and practical tooling for data annotation and fine-tuning. Do you want to create your own custom generative AI models? This is the episode for you! 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. Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! Featuring:Erin Mikail Staples – Mastodon, TwitterDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Label Studio Slides from Erin’s recent PyData talk on RLHF Something missing or broken? PRs welcome!

There are a ton of problems around building LLM apps in production and the last mile of that problem. Travis Fischer, builder of open AI projects like @ChatGPTBot, joins us to talk through these problems (and how to overcome them). He helps us understand the hierarchy of complexity from simple prompting to augmentation, agents, and fine-tuning. Along the way we discuss the frontend developer community that is rapidly adopting AI technology via Typescript (not Python). 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:Travis Fischer – Twitter, GitHubChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: ChatGPT Hacker Community ChatGPTBot Something missing or broken? PRs welcome!

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. 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:Mark Kurtz – Twitter, LinkedInDaniel Whitenack – Twitter, GitHub, WebsiteShow 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 Something missing or broken? PRs welcome!

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. Join the discussionChangelog++ members save 3 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 News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Paul Hünermund – Twitter, LinkedIn, WebsiteChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow 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 Something missing or broken? PRs welcome!

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. 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:Rajiv Shah – Twitter, GitHub, LinkedIn, WebsiteChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow 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 Something missing or broken? PRs welcome!

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?” 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. Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! Featuring:Amanda Wasielewski – Twitter, WebsiteChris Benson – Twitter, GitHub, LinkedIn, WebsiteDaniel Whitenack – Twitter, GitHub, WebsiteShow Notes: Computational Formalism Art History and Machine Learning Something missing or broken? PRs welcome!