Practical AI

Runway is an applied AI research company shaping the next era of art, entertainment & human creativity. Chris sat down with Runway co-founder / CTO, Anastasis Germanidis, to discuss their rise and how it’s defining the future of the creative landscape with its text & image to video models. We hope you find Anastasis’s founder story as inspiring as Chris did.Sponsors:Neo4j – Is your code getting dragged down by JOINs and long query times? The problem might be your database…Try simplifying the complex with graphs. Stop asking relational databases to do more than they were made for. Graphs work well for use cases with lots of data connections like supply chain, fraud detection, real-time analytics, and genAI. With Neo4j, you can code in your favorite programming language and against any driver. Plus, it’s easy to integrate into your tech stack. Visit Neo4j.com/developer to get started. Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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:Anastasis Germanidis – Website, GitHub, LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XShow Notes:Runway | WebsiteRunway | TwitterRunway | AI Film Festival (AIFF)Runway | Gen-2Runway | Gen48Upcoming Events: Register for upcoming webinars here!

While everyone is super hyped about generative AI, computer vision researchers have been working in the background on significant advancements in deep learning architectures. YOLOv9 was just released with some noteworthy advancements relevant to parameter efficient models. In this episode, Chris and Daniel dig into the details and also discuss advancements in parameter efficient LLMs, such as Microsofts 1-Bit LLMs and Qualcomm’s new AI Hub.Sponsors:Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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. Sentry – Launch week! New features and products all week long (so get comfy)! Tune in to Sentry’s YouTube and Discord daily at 9am PT to hear the latest scoop. Too busy? No problem - enter your email address to receive all the announcements (and win swag along the way). Use the code CHANGELOG when you sign up to get $100 OFF the team plan. Typesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! Featuring:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:YOLOv9:Yolov9: Learning What You Want to Learn Using Programmable Gradient InformationYolov9 Object Detection with Programmable Gradient Information (PGI) and Generalized EfficientYolov9: A Comprehensive Guide and Custom Dataset Fine-TuningYOLOv9 SOTA Machine Learning Object Detection ModelYOLOv9Unleashing the Power of YOLOv9YOLOv9 with NNCF and OpenVINOArXiv:2402.13616Parameter efficient LLMs:Hugging Face Paper page, 1-Bit LLMsArXiv paper: “The Era of 1-bit LLMs: All Large Language Models are in 1.58 Bits”Qualcomm AI HubUpcoming Events: Register for upcoming webinars here!

Recently, we briefly mentioned the concept of “Activation Hacking” in the episode with Karan from Nous Research. In this fully connected episode, Chris and Daniel dive into the details of this model control mechanism, also called “representation engineering”. Of course, they also take time to discuss the new Sora model from OpenAI.Sponsors:Neo4j – Is your code getting dragged down by JOINs and long query times? The problem might be your database…Try simplifying the complex with graphs. Stop asking relational databases to do more than they were made for. Graphs work well for use cases with lots of data connections like supply chain, fraud detection, real-time analytics, and genAI. With Neo4j, you can code in your favorite programming language and against any driver. Plus, it’s easy to integrate into your tech stack. Visit Neo4j.com/developer to get started. Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Data synthesis for SOTA LLMs with Karan Malhotra from Nous Research (Practical AI #255)Article: Representation Engineering Mistral-7B an Acid TripOpenAI SoraUpcoming Events: Register for upcoming webinars here!

Chris & Daniel explore AI in national security with Lt. General Jack Shanahan (USAF, Ret.). The conversation reflects Jack’s unique background as the only senior U.S. military officer responsible for standing up and leading two organizations in the United States Department of Defense (DoD) dedicated to fielding artificial intelligence capabilities: Project Maven and the DoD Joint AI Center (JAIC).Together, Jack, Daniel & Chris dive into the fascinating details of Jack’s recent written testimony to the U.S. Senate’s AI Insight Forum on National Security, in which he provides the U.S. government with thoughtful guidance on how to achieve the best path forward with artificial intelligence.Sponsors:Shopify – Sign up for a $1/month trial period at shopify.com/practicalaiFly.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:Jack Shanahan – LinkedInChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Gen AI Master classWritten Testimony of Lieutenant General John (Jack) N.T. Shanahan (USAF, Ret.) AI Insight Forum: National SecuritySoftware Defined Warfare: Architecting the DOD’s Transition to the Digital AgeArtificial Intelligence and Geopolitics:vHitching the Disruptive Technology Cart to the Geopolitics Horse | LinkedInJoint Artificial Intelligence Center (JAIC) | WikipediaUpcoming Events: Register for upcoming webinars here!

Google has been releasing a ton of new GenAI functionality under the name “Gemini”, and they’ve officially rebranded Bard as Gemini. We take some time to talk through Gemini compared with offerings from OpenAI, Anthropic, Cohere, etc.We also discuss the recent FCC decision to ban the use of AI voices in robocalls and what the decision might mean for government involvement in AI in 2024.Sponsors:Neo4j – Is your code getting dragged down by JOINs and long query times? The problem might be your database…Try simplifying the complex with graphs. Stop asking relational databases to do more than they were made for. Graphs work well for use cases with lots of data connections like supply chain, fraud detection, real-time analytics, and genAI. With Neo4j, you can code in your favorite programming language and against any driver. Plus, it’s easy to integrate into your tech stack. Visit Neo4j.com/developer to get started. 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:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:GeminiFCC decision on AI voicesFCC Bans AI Voices in Unsolicited RobocallsPrompt Engineering GuideUpcoming Events: Register for upcoming webinars here!

Nous Research has been pumping out some of the best open access LLMs using SOTA data synthesis techniques. Their Hermes family of models is incredibly popular! In this episode, Karan from Nous talks about the origins of Nous as a distributed collective of LLM researchers. We also get into fine-tuning strategies and why data synthesis works so well.Sponsors:Read Write Own – Read, Write, Own: Building the Next Era of the Internet—a new book from entrepreneur and investor Chris Dixon—explores one possible solution to the internet’s authenticity problem: Blockchains. From AI that tracks its source material to generative programs that compensate—rather than cannibalize—creators. It’s a call to action for a more open, transparent, and democratic internet. One that opens the black box of AI, tracks the origins we see online, and much more. Order your copy of Read, Write, Own today at readwriteown.comFly.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:Karan Malhotra – LinkedInChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Nous on Hugging FaceNous ResearchUpcoming Events: Register for upcoming webinars here!

Recently the release of the rabbit r1 device resulted in huge interest in both the device and “Large Action Models” (or LAMs). What is an LAM? Is this something new? Did these models come out of nowhere, or are they related to other things we are already using? Chris and Daniel dig into LAMs in this episode and discuss neuro-symbolic AI, AI tool usage, multimodal models, and more.Sponsors:Read Write Own – Read, Write, Own: Building the Next Era of the Internet—a new book from entrepreneur and investor Chris Dixon—explores one possible solution to the internet’s authenticity problem: Blockchains. From AI that tracks its source material to generative programs that compensate—rather than cannibalize—creators. It’s a call to action for a more open, transparent, and democratic internet. One that opens the black box of AI, tracks the origins we see online, and much more. Order your copy of Read, Write, Own today at readwriteown.comShopify – Sign up for a $1/month trial period at shopify.com/practicalaiFly.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:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:rabbit r1Salesforce blog on LAMsLangChain toolsMM-LLMs: Recent Advances in MultiModal Large Language ModelsUpcoming Events: Register for upcoming webinars here!

Small changes in prompts can create large changes in the output behavior of generative AI models. Add to that the confusion around proper evaluation of LLM applications, and you have a recipe for confusion and frustration. Raza and the Humanloop team have been diving into these problems, and, in this episode, Raza helps us understand how non-technical prompt engineers can productively collaborate with technical software engineers while building AI-driven apps.Sponsors:Read Write Own – Read, Write, Own: Building the Next Era of the Internet—a new book from entrepreneur and investor Chris Dixon—explores one possible solution to the internet’s authenticity problem: Blockchains. From AI that tracks its source material to generative programs that compensate—rather than cannibalize—creators. It’s a call to action for a more open, transparent, and democratic internet. One that opens the black box of AI, tracks the origins we see online, and much more. Order your copy of Read, Write, Own today at readwriteown.comChangelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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:Raza Habib – LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:HumanloopUpcoming Events: Register for upcoming webinars here!

Recently, Intel’s Liftoff program for startups and Prediction Guard hosted the first ever “Advent of GenAI” hackathon. 2,000 people from all around the world participated in Generate AI related challenges over 7 days. In this episode, we discuss the hackathon, some of the creative solutions, the idea behind it, and more.Sponsors:Read Write Own – Read, Write, Own: Building the Next Era of the Internet—a new book from entrepreneur and investor Chris Dixon—explores one possible solution to the internet’s authenticity problem: Blockchains. From AI that tracks its source material to generative programs that compensate—rather than cannibalize—creators. It’s a call to action for a more open, transparent, and democratic internet. One that opens the black box of AI, tracks the origins we see online, and much more. Order your copy of Read, Write, Own today at readwriteown.comChangelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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:Rahul Nair – GitHub, LinkedIn, XRyan Metz – LinkedIn, XEugenie Wirz – LinkedInRalph de Wargny – LinkedInDaniel Whitenack – Website, GitHub, XShow Notes:Advent of GenAI HackathonIntel’s Liftoff program for startupsPrediction GuardBlog posts: Recap of Day 1Recap of Day 2Recap of Day 3Recap of Day 4Recap of Day 5Final ChallengeUpcoming Events: Register for upcoming webinars here!

We scoured the internet to find all the AI related predictions for 2024 (at least from people that might know what they are talking about), and, in this episode, we talk about some of the common themes. We also take a moment to look back at 2023 commenting with some distance on a crazy AI year.Sponsors:Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XUpcoming Events: Register for upcoming webinars here!

Prashanth Rao mentioned LanceDB as a stand out amongst the many vector DB options in episode #234. Now, Chang She (co-founder and CEO of LanceDB) joins us to talk through the specifics of their open source, on-disk, embedded vector search offering. We talk about how their unique columnar database structure enables serverless deployments and drastic savings (without performance hits) at scale. This one is super practical, so don’t miss it!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.comFly.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:Chang She – GitHub, LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:LanceDBEpisode #234 “Vector DBs beyond the hype”Upcoming Events: Register for upcoming webinars here!

The new open source AI book from PremAI starts with “As a data scientist/ML engineer/developer with a 9 to 5 job, it’s difficult to keep track of all the innovations.” We couldn’t agree more, and we are so happy that this week’s guest Casper (among other contributors) have created this resource for practitioners.During the episode, we cover the key categories to think about as you try to navigate the open source AI ecosystem, and Casper gives his thoughts on fine-tuning, vector DBs & more.Sponsors:Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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.comFly.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:Casper da Costa-Luis – GitHubChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:State of Open Source AI Book - 2023 EditionUpcoming Events: Register for upcoming webinars here!

In this enlightening episode, we delve deeper than the usual buzz surrounding AI’s perils, focusing instead on the tangible problems emerging from the use of machine learning algorithms across Europe. We explore “suspicion machines” — systems that assign scores to welfare program participants, estimating their likelihood of committing fraud. Join us as Justin and Gabriel share insights from their thorough investigation, which involved gaining access to one of these models and meticulously analyzing its behavior.Sponsors:Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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.comFly.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:Gabriel Geiger – XJustin-Casimir Braun – XDaniel Whitenack – Website, GitHub, XShow Notes:Article - “Inside the suspicion machine”The methodology behind Justin and Gabriel’s reportUpcoming Events: Register for upcoming webinars here!

Daniel & Chris conduct a retrospective analysis of the recent OpenAI debacle in which CEO Sam Altman was sacked by the OpenAI board, only to return days later with a new supportive board. The events and people involved are discussed from start to finish along with the potential impact of these events on the AI industry.Sponsors:Traceroute – Listen and follow Season 3 of Traceroute starting November 2 on Apple, Spotify, or wherever you get your podcasts! 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.comFly.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:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:OpenAI | WikipediaHow OpenAI’s origins explain the Sam Altman dramaOpenAI chaos: A timeline of firings, interim CEOs, re-hirings and other twistsOpenAI researchers warned board of AI breakthrough ahead of CEO ouster, sources sayEveryone’s talking about OpenAI’s Q*. Here’s what you need to know about the mysterious project.It is Time to Profit off of the OpenAI DramaYann LeCun | LinkedInAdvent of GenAI HackathonUpcoming Events: Register for upcoming webinars here!

Shopify recently released a Hugging Face space demonstrating very impressive results for replacing background scenes in product imagery. In this episode, we hear the backstory technical details about this work from Shopify’s Russ Maschmeyer. Along the way we discuss how to come up with clever AI solutions (without training your own model).Sponsors:Advent of GenAI Hackathon – Join us for a 7-day journey into the world of Generative AI with the Advent of GenAI Hackathon. Learn more here! Traceroute – Listen and follow Season 3 of Traceroute starting November 2 on Apple, Spotify, or wherever you get your podcasts! Featuring:Russ Maschmeyer – GitHub, LinkedIn, Mastodon, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Advent of GenAI HackathonShopify’s HF Space for background replacementShopify MagicUpcoming Events: Register for upcoming webinars here!

According to Solana Larsen: “Too often, it feels like we have lost control of the internet to the interests of Big Tech, Big Data — and now Big AI.” In the latest season of Mozilla’s IRL podcast (edited by Solana), a number of stories are featured to highlight the trailblazers who are reclaiming power over AI to put people first. We discuss some of those stories along with the issues that they surface.Sponsors:Traceroute Podcast – Listen and follow Season 3 of Traceroute starting November 2 on Apple, Spotify, or wherever you get your podcasts! 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.comFly.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:Solana Larsen – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Blog post announcing this season of IRL about putting people first in AIThe IRL podcastUpcoming Events: Register for upcoming webinars here!

On Monday, October 30, 2023, the U.S. White House issued its Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial Intelligence. Two days later, a policy paper was issued by the U.K. government entitled The Bletchley Declaration by Countries Attending the AI Safety Summit, 1-2 November 2023. It was signed by 29 countries, including the United States and China, the global leaders in AI research.In this Fully Connected episode, Daniel and Chris parse the details and highlight key takeaways from these documents, especially the extensive and detailed executive order, which has the force of law in the United States.Sponsors:Traceroute Podcast – Listen and follow Season 3 of Traceroute starting November 2 on Apple, Spotify, or wherever you get your podcasts! Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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.comFeaturing:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Executive Order on the Safe, Secure, and Trustworthy Development and Use of Artificial IntelligenceFACT SHEET: President Biden Issues Executive Order on Safe, Secure, and Trustworthy Artificial IntelligenceThe Bletchley Declaration by Countries Attending the AI Safety Summit, 1-2 November 2023Upcoming Events: Register for upcoming webinars here!

We’re excited to have Tuhin join us on the show once again to talk about self-hosting open access models. Tuhin’s company Baseten specializes in model deployment and monitoring at any scale, and it was a privilege to talk with him about the trends he is seeing in both tooling and usage of open access models. We were able to touch on the common use cases for integrating self-hosted models and how the boom in generative AI has influenced that ecosystem.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.comFly.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:Tuhin Srivastava – GitHub, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:BasetenUpcoming Events: Register for upcoming webinars here!

It seems like everyone is interested in Rust these days. Even the most popular Python linter, Ruff, isn’t written in Python! It’s written in Rust. But what is the state of training or inferencing deep learning models in Rust? In this episode, we are joined by Nathaniel Simard, the creator burn. We discuss Rust in general, the need to have support for AI in multiple languages, and the current state of doing “AI things” in Rust.Sponsors:Neo4j – NODES 2023 is coming in October! 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.comFly.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:Nathaniel Simard – GitHub, LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:burn-rs: This library strives to serve as a comprehensive deep learning framework, offering exceptional flexibility and written in Rust.Upcoming Events: Register for upcoming webinars here!

Chris & Daniel are out this week, so we’re bringing you a panel discussion from All Things Open 2023 moderated by Jerod Santo (Practical AI producer and co-host of The Changelog) and featuring keynoters Emily Freeman and James Q Quick.Sponsors:Neo4j – NODES 2023 is coming in October! 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.comFly.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:Emily Freeman – Website, GitHub, Mastodon, XJames Q Quick – Website, GitHub, XJerod Santo – GitHub, LinkedIn, Mastodon, XUpcoming Events: Register for upcoming webinars here!

What is the model lifecycle like for experimenting with and then deploying generative AI models? Although there are some similarities, this lifecycle differs somewhat from previous data science practices in that models are typically not trained from scratch (or even fine-tuned). Chris and Daniel give a high level overview in this effort and discuss model optimization and serving.Sponsors:Neo4j – NODES 2023 is coming in October! 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.comFly.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:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:BigDLArticle: Making LLMs even more accessible with bitsandbytes, 4-bit quantization and QLoRAPrevious episode: Running large models on CPUsBaseten’s TrussSeldonHugging Face’s TGIIntel Gaudi 2Intel TDXUpcoming Events: Register for upcoming webinars here!

Dominik Klotz from askui joins Daniel and Chris to discuss the automation of UI, and how AI empowers them to automate any use case on any operating system. Along the way, the trio explore various approaches and the integration of generative AI, large language models, and computer vision.Sponsors:Statsig – Build faster with confidence. Startups to Fortune 500s rely on Statsig to make data-driven decisions. Ship smarter and faster with the unified platform for feature flags, experimentation, and analytics. Our listeners get free white-glove onboarding, migration support, and 5 million free events per month. Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. 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.comFly.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:Dominik Klotz – GitHub, LinkedInChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:askui.comaskui on GitHubaskui on LinkedInaskui on Twitter/XUpcoming Events: Register for upcoming webinars here!

In this episode we welcome back our good friend Demetrios from the MLOps Community to discuss fine-tuning vs. retrieval augmented generation. Along the way, we also chat about OpenAI Enterprise, results from the MLOps Community LLM survey, and the orchestration and evaluation of generative AI workloads.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.comFly.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:Demetrios Brinkmann – XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:MLOps CommunityLLM survey reportLLMs in Production Event - Part IIIUpcoming Events: Register for upcoming webinars here!

You might have heard a lot about code generation tools using AI, but could LLMs and generative AI make our existing code better? In this episode, we sit down with Mike from TurinTech to hear about practical code optimizations using AI “translation” of slow to fast code. We learn about their process for accomplishing this task along with impressive results when automated code optimization is run on existing open source projects.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.comFly.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! Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Mike Basios – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:TurinTech AIUpcoming Events: Register for upcoming webinars here!

Recently a16z released a diagram showing the “Emerging Architectures for LLM Applications.” In this episode, we expand on things covered in that diagram to a more general mental model for the new AI app stack. We cover a variety of things from model “middleware” for caching and control to app orchestration.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.comFly.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! Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Emerging Architectures for LLM ApplicationsUpcoming Events: Register for upcoming webinars here!

In this Fully Connected episode, Daniel and Chris kick it off by noting that Stability AI released their SDXL 1.0 LLM! They discuss its virtues, and then dive into a discussion regarding how the United States, European Union, and other entities are approaching governance of AI through new laws and legal frameworks. In particular, they review the White House’s approach, noting the potential for unexpected consequences.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.comFly.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! Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Announcing SDXL 1.0GitHub, Hugging Face, urge EU to relax open-source AI rulesWhite House: Blueprint for an AI Bill of RightsLEARNING RESOURCE!Patterns for Building LLM-based Systems & ProductsUpcoming Events: Register for upcoming webinars here!

There’s so much talk (and hype) these days about vector databases. We thought it would be timely and practical to have someone on the show that has been hands on with the various options and actually tried to build applications leveraging vector search. Prashanth Rao is a real practitioner that has spent and huge amount of time exploring the expanding set of vector database offerings. After introducing vector database and giving us a mental model of how they fit in with other datastores, Prashanth digs into the trade offs as related to indices, hosting options, embedding vs. query optimization, 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.comFly.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! Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Prashanth Rao – Website, GitHub, LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Vector databases blog posts from Prashanth:(Part 1): What makes each one different?(Part 2): Understanding their internals(Part 3): Not all indexes are created equalUpcoming Events: Register for upcoming webinars here!

It was an amazing week in AI news. Among other things, there is a new NeRF and a new Llama in town!!! Zip-NeRF can create some amazing 3D scenes based on 2D images, and Llama 2 from Meta promises to change the LLM landscape. Chris and Daniel dive into these and they compare some of the recently released OpenAI functionality to Anthropic’s Claude 2.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.comFly.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:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:What is NeRF articleLlama 2: Llama 2 siteLlama 2 paperOpenAI Code InterpreterAnthropic Claude 2Learning resources:Hugging Face guide to Llama 2LLaMA 2 - Every Resource you needOpenAI code interpreter articleUpcoming Events: Register for upcoming webinars here!

As a technologist, coder, and lawyer, few people are better equipped to discuss the legal and practical consequences of generative AI than Damien Riehl. He demonstrated this a couple years ago by generating, writing to disk, and then releasing every possible musical melody. Damien joins us to answer our many questions about generated content, copyright, dataset licensing/usage, and the future of knowledge work.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.comFly.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:Damien Riehl – LinkedIn, Mastodon, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Talk - Legal and Practical Consequences of Generative AI (LLMs like GPT, Bart, PaLM, LLaMA, Alpaca, Codex)Talk - Why All Melodies Should Be Free for Musicians to Use | Damien Riehl | TEDUpcoming Events: Register for upcoming webinars here!

Chris sat down with Varun Mohan and Anshul Ramachandran, CEO / Cofounder and Lead of Enterprise and Partnership at Codeium, respectively. They discussed how to streamline and enable modern development in generative AI and large language models (LLMs). Their new tool, Codeium, was born out of the insights they gleaned from their work in GPU software and solutions development, particularly with respect to generative AI, large language models, and supporting infrastructure. Codeium is a free AI-powered toolkit for developers, with in-house models and infrastructure - not another API wrapper.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.comFly.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:Varun Mohan – LinkedInAnshul Ramachandran – LinkedInChris Benson – Website, GitHub, LinkedIn, XShow Notes:CodeiumWhat GitHub Copilot Lacks: Fine-tuning on Your Private CodeUpcoming Events: Register for upcoming webinars here!

In this Fully Connected episode, Daniel and Chris explore recent highlights from the current model proliferation wave sweeping the world - including Stable Diffusion XL, OpenChat, Zeroscope XL, and Salesforce XGen. They note the rapid rise of open models, and speculate that just as in open source software, open models will dominate the future. Such rapid advancement creates its own problems though, so they finish by itemizing concerns such as cybersecurity, workflow productivity, and impact on human culture.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.comFly.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! Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Chris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Stable Diffusion XL 0.9OpenChatZeroscope XLSalesforce XGenAI is Eating The WorldLLM universityUpcoming Events: Register for upcoming webinars here!

Your feed might be dominated by LLMs these days, but there are some amazing things happening in computer vision that you shouldn’t ignore! In this episode, we bring you one of those amazing stories from Gabriel Ortiz, who is working with the government of Cantabria in Spain to automate cartography and apply AI to geospatial analysis. We hear about how AI tooling fits into the GIS workflow, and Gabriel shares some of his recent work (including work that can identify individual people, invasive plant species, building and more from aerial survey data).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.comFly.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! Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Gabriel Ortiz – LinkedInDaniel Whitenack – Website, GitHub, XShow Notes:Automated cartography (integration of different models: buildings, roads, vegetation)Detecting and tracking the expansion of forests (period 1957-2020) using both legacy and modern imageryTracking invader speciesTracking urban growth with AISpatial behavior in beaches using AIInference with SAM (Meta’s Segment Anything Model) over urban areas/viewer.html?webmap=4af373c294e24394ae25e4acadab71ccSuperResolution on aerial or satellite imageryMore of the work of Gabriel and his team can be seen here and also on his LinkedIn profileUpcoming Events: Register for upcoming webinars here!

Chris and Daniel take a step back to look at how generative AI fits into the wider landscape of ML/AI and data science. They talk through the differences in how one approaches “traditional” supervised learning and how practitioners are approaching generative AI based solutions (such as those using Midjourney or GPT family models). Finally, they talk through the risk and compliance implications of generative AI, which was in the news this week in the EU.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.comFly.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 – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:NYT Article: “Europeans Take a Major Step Toward Regulating A.I.”Upcoming Events: Register for upcoming webinars here!

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!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.comFly.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 – Website, GitHub, XAlessio Fanelli – Website, GitHub, XDaniel Whitenack – Website, GitHub, XShow Notes:Latent Space podcastFeatured Latent Space episodes: BenchmarksReza ShabaniMosaicML and MPTSegment AnythingMike ConoverFeatured Practical AI episodes: From notebooks to Netflix scale with MetaflowCapabilities of LLMs 🤯 ML at small organizationsPrediction GuardData DanUpcoming Events: Register for upcoming webinars here!

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!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.comFly.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 – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Lately.AIUpcoming Events: Register for upcoming webinars here!

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.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.comFly.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 – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Prediction GuardPrediction Guard docsLLMs in Production II eventUpcoming Events: Register for upcoming webinars here!

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.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.comFly.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 – GitHub, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:LlamaIndex DocsLlamaHubLlamaIndex BlogUpcoming Events: Register for upcoming webinars here!

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!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.comFly.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, XDaniel Whitenack – Website, GitHub, XShow Notes:Label StudioSlides from Erin’s recent PyData talk on RLHFUpcoming Events: Register for upcoming webinars here!

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).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.comFly.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 – GitHub, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:ChatGPT Hacker CommunityChatGPTBotUpcoming Events: Register for upcoming webinars here!

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.comFly.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, XDaniel Whitenack – Website, GitHub, XShow Notes:Neural MagicSparseMLSparseZooNeural Magic Scales up MLPerf™ Inference v3.0 Performance With Demonstrated Power Efficiency; No GPUs NeededDeploy Optimized Hugging Face Models With DeepSparse and SparseZooSparseGPT: Remove 100 Billion Parameters for FreeUpcoming Events: Register for upcoming webinars here!

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.comFly.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, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:How Can Causal Machine Learning Improve Business Decisions?Causal Inference is More than Fitting the Data WellCausal Data Science in PracticeCausal DiscoveryDoWhy GithubThe Book of WhyCausal Data Science MeetingPaul’s study on causal ML adoption in industry (incl. an overview of useful software packages in Table 3)Causal Data Science MOOC on UdemyUpcoming Events: Register for upcoming webinars here!

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.comFly.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, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Solving AI Tasks with ChatGPT and its Friends in HuggingFace | GitHubGenerative Agents: Interactive Simulacra of Human BehaviorWolfram ChatGPTComparing LLMsLangChainLearn about LLMs: Emergence and reasoning in large language models (Jason Wei)Sparks of Artificial General IntelligenceLearning PromptingGetting Started with Transformers: Transformers course (free)Tasks at Hugging FaceTraining your own LLM Models: Efficient Large Language Model training with LoRA and Hugging FacePEFT (Parameter-Efficient Fine-Tuning)Dolly blog postIllustrating Reinforcement Learning from Human FeedbackUpcoming Events: Register for upcoming webinars here!

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.comFly.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, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Computational Formalism Art History and Machine LearningUpcoming Events: Register for upcoming webinars here!

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.comFly.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, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Christof Henkel | KaggleNVIDIA Kaggle GrandmastersKaggleNVIDIA RAPIDSNVIDIA Data Loading Library (DALI)Upcoming Events: Register for upcoming webinars here!

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.comTypesense – Lightning fast, globally distributed Search-as-a-Service that runs in memory. You literally can’t get any faster! Featuring:Beth Rudden – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Bast.aiUpcoming Events: Register for upcoming webinars here!

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.comFly.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, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:You.comOpen Platform for developersJoin the You.com Discord serverUpcoming Events: Register for upcoming webinars here!

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.comFly.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, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:ModalEpisode 142 discussing Erik’s “building a data team” articleUpcoming Events: Register for upcoming webinars here!

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.comFly.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 railsA Conversation With Bing’s Chatbot Left Me Deeply UnsettledSydney’s gaslightingChatGPT political biasStable Diffusion amplification of stereotypesUseful guides related to prompt engineering:co:here prompt engineering guidePrompt engineering overview from Elvis Savaria10 Amazing Resources For Prompt Engineering, ChatGPT, and GPT-3Image generation prompt engineering guides: see here and hereUpcoming Events: Register for upcoming webinars here!

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.comFly.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:hereTopically sandbox - topic modelingco:here’s prompt engineering guideUpcoming Events: Register for upcoming webinars here!

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!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.comFly.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.Upcoming Events: Register for upcoming webinars here!