Practical AI

We’ve all heard about breaches of privacy and leaks of private health information (PHI). For healthcare providers and those storing this data, knowing where all the sensitive data is stored is non-trivial. Ramin, from Tausight, joins us to discuss how they have deploy edge AI models to help company search through billions of records for PHI.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. Backblaze – Unlimited cloud backup for Macs, PCs, and businesses for just $99/year. Easily protect business data through a centrally managed admin. Protect all the data on your machines automatically. Easy to deploy across multiple workstations with various deployment options. Featuring:Ramin Mohammadi – GitHub, LinkedInDaniel Whitenack – Website, GitHub, XShow Notes:TausightUpcoming Events: Register for upcoming webinars here!

We’ve seen a rise in interest recently and a number of major announcements related to local LLMs and AI PCs. NVIDIA, Apple, and Intel are getting into this along with models like the Phi family from Microsoft. In this episode, we dig into local AI tooling, frameworks, and optimizations to help you navigate this AI niche, and we talk about how this might impact AI adoption in the longer term.Sponsors:Ladder Life Insurance – 100% digital — no doctors, no needles, no paperwork. Don’t put it off until the very last minute to get term coverage life insurance through Ladder. Find out if you’re instantly approved. They’re rated A and A plus. Life insurance costs more as you age, now’s the time to cross it off your list. 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. 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:OllamaLM Studiollama.cppOpenVINOMLPerf client working groupArticle - 5 top small language modelsGPTQ articleArticle - Which quantization method is right for youUpcoming Events: Register for upcoming webinars here!

At the age of 72, U.S. Representative Don Beyer of Virginia enrolled at GMU to pursue a Master’s degree in C.S. with a concentration in Machine Learning.Rep. Beyer is Vice Chair of the bipartisan Artificial Intelligence Caucus & Vice Chair of the NDC’s AI Working Group. He is the author of the AI Foundation Model Transparency Act & a lead cosponsor of the CREATE AI Act, the Federal Artificial Intelligence Risk Management Act & the Artificial Intelligence Environmental Impacts Act.We hope you tune into this inspiring, nonpartisan conversation with Rep. Beyer about his decision to dive into the deep end of the AI pool & his leadership in bringing that expertise to Capitol Hill.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. Featuring:Don Beyer – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:U.S. Representative Don BeyerCongressman Don Beyer, Mason student and lifelong learnerBeyer Statement On President Biden’s AI Executive OrderBeyer Appointed To Bipartisan Task Force On Artificial IntelligenceUpcoming Events: Register for upcoming webinars here!

Daniel & Chris share their first impressions of OpenAI’s newest LLM: GPT-4o and Daniel tries to bring the model into the conversation with humorously mixed results. Together, they explore the implications of Omni’s new feature set - the speed, the voice interface, and the new multimodal capabilities.Sponsors:Ladder Life Insurance – 100% digital — no doctors, no needles, no paperwork. Don’t put it off until the very last minute to get term coverage life insurance through Ladder. Find out if you’re instantly approved. They’re rated A and A plus. Life insurance costs more as you age, now’s the time to cross it off your list. 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. Featuring:Daniel Whitenack – Website, GitHub, XChris Benson – Website, GitHub, LinkedIn, XShow Notes:Hello GPT-4oAI Engineer World’s FairAIQCON - the AI Quality ConferenceBrave New Words: How AI Will Revolutionize Education (and Why That’s a Good Thing)Upcoming Events: Register for upcoming webinars here!

There’s a lot of hype about AI agents right now, but developing robust agents isn’t yet a reality in general. Imbue is leading the way towards more robust agents by taking a full-stack approach; from hardware innovations through to user interface. In this episode, Josh, Imbue’s CTO, tell us more about their approach and some of what they have learned along the way.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. 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:Josh Albrecht – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:CARBS (Imbue’s cost-aware hyperparameter optimizer)Imbue paper on the stepwise nature of self-supervised learningA paper on initialization/feature learning co-authored by Jamie Simon, a member of Imbue’s technical teamImbueUpcoming Events: Register for upcoming webinars here!

Yep, you heard that right. Autonomous fighter jets are in the news. Chris and Daniel discuss a modified F-16 known as the X-62A VISTA and autonomous vehicles/ systems more generally. They also comment on the Linux Foundation’s new Open Platform for Enterprise AI.Sponsors:Ladder Life Insurance – 100% digital — no doctors, no needles, no paperwork. Don’t put it off until the very last minute to get term coverage life insurance through Ladder. Find out if you’re instantly approved. They’re rated A and A plus. Life insurance costs more as you age, now’s the time to cross it off your list. 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:Pentagon takes AI dogfighting to next level in real-world flight tests against human F-16 pilotTop US Air Force official rides in front seat of autonomous F-16Open Platform for Enterprise AIUpcoming Events: Register for upcoming webinars here!

We recently gathered some Practical AI listeners for a live webinar with Danny from LibreChat to discuss the future of private, open source chat UIs. During the discussion we hear about the motivations behind LibreChat, why enterprise users are hosting their own chat UIs, and how Danny (and the LibreChat community) is creating amazing features (like RAG and plugins).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. Featuring:Danny Avila – XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Register for our next webinar (similar to this one) focused on multimodal AILibreChatPrediction GuardUpcoming Events: Register for upcoming webinars here!

First there was Mamba… now there is Jamba from AI21. This is a model that combines the best non-transformer goodness of Mamba with good ‘ol attention layers. This results in a highly performant and efficient model that AI21 has open sourced! We hear all about it (along with a variety of other LLM things) from AI21’s co-founder Yoav.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. Changelog News – A podcast+newsletter combo that’s brief, entertaining & always on-point. Subscribe today. Featuring:Yoav Shoham – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:Jamba - A Groundbreaking SSM - Transformer Open ModelAI21 LabsUpcoming Events: Register for upcoming webinars here!

2024 promises to be the year of multi-modal AI, and we are already seeing some amazing things. In this “fully connected” episode, Chris and Daniel explore the new Udio product/service for generating music. Then they dig into the differences between recent multi-modal efforts and more “traditional” ways of combining data modalities.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. 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:UdioCLIPBridgeTowerLLaVAUpcoming Events: Register for upcoming webinars here!

Daniel & Chris delight in conversation with “the funniest guy in AI”, Demetrios Brinkmann. Together they explore the results of the MLOps Community’s latest survey. They also preview the upcoming AI Quality Conference.Sponsors:The Hacker Mindset – “The Hacker Mindset” written by Garrett Gee, a seasoned white hat hacker with over 20 years of experience, is available for pre-order now. This book reveals the secrets of white hat hacking and how you can apply them to overcome obstacles and achieve your goals. In a world where hacking often gets a bad rap, this book shows you the white hat side – the side focused on innovation, problem-solving, and ethical principles. 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:Demetrios Brinkmann – XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:MLOps CommunityAI Quality ConferenceEvaluation SurveyRAG failover talk from Jerry LuiPrompt Templates the SongUpcoming Events: Register for upcoming webinars here!

In this fully connected episode, Daniel & Chris discuss NVIDIA GTC keynote comments from CEO Jensen Huang about teaching kids to code. Then they dive into the notion of “community” in the AI world, before discussing challenges in the adoption of generative AI by non-technical people. They finish by addressing the evolving balance between generative AI interfaces and search engines.Sponsors:Ladder Life Insurance – 100% digital — no doctors, no needles, no paperwork. Don’t put it off until the very last minute to get term coverage life insurance through Ladder. Find out if you’re instantly approved. They’re rated A and A plus. Life insurance costs more as you age, now’s the time to cross it off your list. 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:NVIDIA GTC March 2024 Keynote with NVIDIA CEO Jensen Huang5 Forces That Will Drive the Adoption of GenAI | Harvard Business ReviewHere’s why AI search engines really can’t kill Google | The VergeUpcoming Events: Register for upcoming webinars here!

Daniel and Chris are out this week, so we’re bringing you conversations all about AI’s complicated relationship to software developers from other Changelog pods: JS Party, Go Time & The Changelog.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. The Hacker Mindset – “The Hacker Mindset” written by Garrett Gee, a seasoned white hat hacker with over 20 years of experience, is available for pre-order now. This book reveals the secrets of white hat hacking and how you can apply them to overcome obstacles and achieve your goals. In a world where hacking often gets a bad rap, this book shows you the white hat side – the side focused on innovation, problem-solving, and ethical principles. 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:Kent Quirk – GitHub, Mastodon, XSharon DiOrio – XSteven Pyle – LinkedInJosé Valim – Website, GitHub, XJerod Santo – GitHub, LinkedIn, Mastodon, XKevin Ball – Website, GitHub, LinkedIn, XNick Nisi – Website, GitHub, Mastodon, XJohnny Boursiquot – Website, GitHub, XAdam Stacoviak – Website, GitHub, LinkedIn, Mastodon, XShow Notes:JS Party #317 (This will 404 until Thursday!)Go Time #306Changelog & Friends #28Upcoming Events: Register for upcoming webinars here!

Daniel & Chris explore the state of the art in prompt engineering with Jared Zoneraich, the founder of PromptLayer. PromptLayer is the first platform built specifically for prompt engineering. It can visually manage prompts, evaluate models, log LLM requests, search usage history, and help your organization collaborate as a team. Jared provides expert guidance in how to be implement prompt engineering, but also illustrates how we got here, and where we’re likely to go next.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:Jared Zoneraich – LinkedIn, XChris Benson – Website, GitHub, LinkedIn, XDaniel Whitenack – Website, GitHub, XShow Notes:PromptLayerUpcoming Events: Register for upcoming webinars here!

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!