Practical AI: Machine Learning, Data Science
279 episodes - English - Latest episode: 5 days ago - ★★★★★ - 37 ratingsMaking artificial intelligence practical, productive & accessible to everyone. Practical AI is a show in which technology professionals, business people, students, enthusiasts, and expert guests engage in lively discussions about Artificial Intelligence and related topics (Machine Learning, Deep Learning, Neural Networks, GANs, MLOps, AIOps, LLMs & more). The focus is on productive implementations and real-world scenarios that are accessible to everyone. If you want to keep up with the latest advances in AI, while keeping one foot in the real world, then this is the show for you!
Homepage Apple Podcasts Google Podcasts Overcast Castro Pocket Casts RSS feed
Episodes
The perplexities of information retrieval
June 19, 2024 16:30 - 46 minutes - 42.5 MBDaniel & Chris sit down with Denis Yarats, Co-founder & CTO at Perplexity, to discuss Perplexity’s sophisticated AI-driven answer engine. Denis outlines some of the deficiencies in search engines, and how Perplexity’s approach to information retrieval improves on traditional search engine systems, with a focus on accuracy and validation of the information provided.
Using edge models to find sensitive data
June 13, 2024 16:45 - 38 minutes - 35.4 MBWe’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.
Rise of the AI PC & local LLMs
June 04, 2024 18:45 - 35 minutes - 32.8 MBWe’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.
AI in the U.S. Congress
May 29, 2024 14:30 - 40 minutes - 37.6 MBAt 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 y...
First impressions of GPT-4o
May 22, 2024 00:30 - 43 minutes - 40 MBDaniel & 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.
Full-stack approach for effective AI agents
May 15, 2024 14:00 - 47 minutes - 43.3 MBThere’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.
Autonomous fighter jets?!
May 08, 2024 19:00 - 41 minutes - 37.9 MBYep, 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.
Private, open source chat UIs
April 30, 2024 20:45 - 38 minutes - 35.4 MBWe 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).
Mamba & Jamba
April 24, 2024 15:45 - 41 minutes - 38 MBFirst 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.
Udio & the age of multi-modal AI
April 16, 2024 18:20 - 38 minutes - 35.8 MB2024 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.
RAG continues to rise
April 10, 2024 14:00 - 48 minutes - 44.5 MBDaniel & 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.
Should kids still learn to code?
April 02, 2024 20:00 - 39 minutes - 36.2 MBIn 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.
AI vs software devs
March 26, 2024 19:30 - 57 minutes - 52.4 MBDaniel 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.
Prompting the future
March 20, 2024 13:45 - 46 minutes - 42.4 MBDaniel & 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.
Generating the future of art & entertainment
March 12, 2024 17:00 - 42 minutes - 38.8 MBRunway 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.
YOLOv9: Computer vision is alive and well
March 06, 2024 17:00 - 42 minutes - 39.4 MBWhile 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.
Representation Engineering (Activation Hacking)
February 28, 2024 15:00 - 43 minutes - 40.1 MBRecently, 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.
Leading the charge on AI in National Security
February 20, 2024 15:15 - 52 minutes - 47.9 MBChris & 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 testi...
Gemini vs OpenAI
February 14, 2024 20:00 - 43 minutes - 40 MBGoogle 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.
Data synthesis for SOTA LLMs
February 06, 2024 22:00 - 46 minutes - 43.2 MBNous 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.
Large Action Models (LAMs) & Rabbits 🐇
January 30, 2024 21:00 - 48 minutes - 44.4 MBRecently 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.
Collaboration & evaluation for LLM apps
January 23, 2024 22:30 - 46 minutes - 42.6 MBSmall 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.
Advent of GenAI Hackathon recap
January 17, 2024 20:00 - 47 minutes - 44 MBRecently, 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.
AI predictions for 2024
January 10, 2024 19:30 - 45 minutes - 41.4 MBWe 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.
Open source, on-disk vector search with LanceDB
December 19, 2023 19:40 - 41 minutes - 38.5 MBPrashanth 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!
The state of open source AI
December 12, 2023 19:45 - 42 minutes - 39.2 MBThe 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.
Suspicion machines ⚙️
December 05, 2023 21:45 - 46 minutes - 43.2 MBIn 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 ana...
The OpenAI debacle (a retrospective)
November 29, 2023 18:00 - 47 minutes - 43.4 MBDaniel & 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.
Generating product imagery at Shopify
November 21, 2023 18:45 - 50 minutes - 46.2 MBShopify 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).
AI trailblazers putting people first
November 14, 2023 17:45 - 47 minutes - 43.9 MBAccording 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.
Government regulation of AI has arrived
November 07, 2023 14:00 - 45 minutes - 41.5 MBOn 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 deta...
Self-hosting & scaling models
October 31, 2023 18:00 - 41 minutes - 37.9 MBWe’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.
Deep learning in Rust with Burn 🔥
October 24, 2023 20:40 - 40 minutes - 37.4 MBIt 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.
AI's impact on developers
October 20, 2023 16:30 - 48 minutes - 44.5 MBChris & 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.
Generative models: exploration to deployment
October 03, 2023 19:00 - 49 minutes - 45.1 MBWhat 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.
Automate all the UIs!
September 20, 2023 16:00 - 43 minutes - 39.6 MBDominik 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.
Fine-tuning vs RAG
September 06, 2023 12:30 - 58 minutes - 53.4 MBIn 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.
Automating code optimization with LLMs
August 29, 2023 21:30 - 45 minutes - 41.4 MBYou 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.
The new AI app stack
August 23, 2023 12:00 - 45 minutes - 41.5 MBRecently 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.
Blueprint for an AI Bill of Rights
August 09, 2023 16:20 - 41 minutes - 38.3 MBIn 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.
Vector databases (beyond the hype)
August 01, 2023 18:30 - 51 minutes - 47.4 MBThere’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, Pras...
There's a new Llama in town
July 25, 2023 19:00 - 48 minutes - 44.3 MBIt 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.
Legal consequences of generated content
July 18, 2023 18:30 - 42 minutes - 39.5 MBAs 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.
A developer's toolkit for SOTA AI
July 12, 2023 21:00 - 42 minutes - 38.7 MBChris 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 A...
Cambrian explosion of generative models
July 06, 2023 17:30 - 42 minutes - 38.8 MBIn 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...
Automated cartography using AI
June 28, 2023 14:30 - 44 minutes - 41.1 MBYour 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...
From ML to AI to Generative AI
June 21, 2023 13:30 - 46 minutes - 42.9 MBChris 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.
AI trends: a Latent Space crossover
June 14, 2023 19:00 - 59 minutes - 54.8 MBDaniel 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!
Accidentally building SOTA AI
June 06, 2023 20:45 - 42 minutes - 38.7 MBLately.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!
Controlled and compliant AI applications
May 31, 2023 17:00 - 49 minutes - 45.7 MBYou 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 outpu...