Your queries are on a spectrum. Head Tail High Volume Low Volume General Specific Few Queries Many Queries When we talk about volume, we talk about the amount of searches with the same query term. Tail queries still have a large volume of search volume, but as a distribution. What counts into the head, torso, and tail que…

From building a data platform and Parquet at Twitter to using AI to make biology easier to engineer at Ginkgo Bioworks, Dmitriy joins the show to chat about the early days of big data, the conversation that made him jump into SynBio, LLMs for proteins and more. Segments: (00:03:18) Data engineering roots (00:05:40) Early influences at Lawrence Berk…

Welcome back to How AI Is Built. We have got a very special episode to kick off season two. Daniel Tunkelang is a search consultant currently working with Algolia. He is a leader in the field of information retrieval, recommender systems, and AI-powered search. He worked for Canva, Algolia, Cisco, Gartner, Handshake, to pick a few. His core focus i…

Facets let your users tune their search results. They are not filters. Filters eliminate search results. Facets give users the ability to reduce the search results. Facets allow the user in the frontend to limit the search results to a limited, more specific set. They are extremely valuable in combination with head queries (reference), which return…

A veteran of early Twitter's fail whale wars, Dmitriy joins the show to chat about the time when 70% of the Hadoop cluster got accidentally deleted, the financial reality of writing a book, and how to navigate acquisitions. Segments: (00:00:00) The Infamous Hadoop Outage (00:02:36) War Stories from Twitter's Early Days (00:04:47) The Fail Whale Era…

Today we are launching the season 2 of How AI Is Built. The last few weeks, we spoke to a lot of regular listeners and past guests and collected feedback. Analyzed our episode data. And we will be applying the learnings to season 2. This season will be all about search. We are trying to make it better, more actionable, and more in-depth. The goal i…

Known for hosting the CoRecursive podcast, which dives into the stories behind the code, Adam joins the show to chat about discovering that the great engineers he had looked up to are actually great communicators, his framework for building one of the best storytelling engineering podcasts, and the journey getting into DevRel. Chapters: (00:00:00) …

As the original architect and API design lead of Kubernetes, Brian joins the show to chat about why "APIs are forever", the keys to evangelizing impactful projects, and being an Uber Tech at Google, and more. Segments: (00:03:01) Internship with Mark Ewing (00:07:10) “Mark and Brian's Excellent Environment” manual (00:11:58) Poker on VT100 terminal…

Today Matthew and I reminisce about early childhood memories like kicking Dad in the nuts, being stung by a swarm of bees, the "NBA Jam Slap", and some of our most shameful moments like the "Black and White Stick", and much more. Also Matthew mentioned a movie called "The PeanutButter Gang" when in fact the movie he's referring to is called The But…

From building a new kind of server to building a new kind of company, co-founders Bryan and Steve join the show to chat about their "meet cute" and the origin story of Oxide, their unconventional recruiting process, transparent and uniform salaries, and their solution to the "N+1 shithead problem". Segments: (00:03:03) Bryan and Steve's "meet cute"…

In this episode of "How AI is Built," host Nicolay Gerold interviews Jonathan Yarkoni, founder of Reach Latent. Jonathan shares his expertise in extracting value from unstructured data using AI, discussing challenging projects, the impact of ChatGPT, and the future of generative AI. From weather prediction to legal tech, Jonathan provides valuable …

This episode of "How AI Is Built" is all about data processing for AI. Abhishek Choudhary and Nicolay discuss Spark and alternatives to process data so it is AI-ready. Spark is a distributed system that allows for fast data processing by utilizing memory. It uses a dataframe representation "RDD" to simplify data processing. When should you use Spar…

Having quit Google in 2018 to bootstrap indie software businesses, Michael is known for writing very transparently about the ups and downs of his journey. After recently selling his hardware business TinyPilot for $600K, Michael returns to the show to chat about the misconceptions about running an indie business, the hardest part of selling a compa…

Like the song goes, “Opportunity comes once in a lifetime, Yo.” Then, “Something… Something… Mom’s Spaghetti!” And like the song this episode of the Savage FINcast is about missing opportunity. Craig, Raven, Jim, and Mark take a look at Savage Dragon 271 as several running plot threads seem to pop off while another heads turns a major corner. Do th…

In this episode, Nicolay talks with Rahul Parundekar, founder of AI Hero, about the current state and future of AI agents. Drawing from over a decade of experience working on agent technology at companies like Toyota, Rahul emphasizes the importance of focusing on realistic, bounded use cases rather than chasing full autonomy. They dive into the ke…

Well-known for his insightful and meticulous write-ups on testing distributed systems, Kyle (aka Aphyr) joins the show to chat about the origins of Jepsen, how he built a business around testing distributed systems, his writing process, favorite databases, and more. Segments: (00:03:29) From Physics to Software Engineering (00:07:47) The origins of…

In this conversation, Nicolay and Richmond Alake discuss various topics related to building AI agents and using MongoDB in the AI space. They cover the use of agents and multi-agents, the challenges of controlling agent behavior, and the importance of prompt compression. When you are building agents. Build them iteratively. Start with simple LLM ca…

From creating one of the Python’s most influential libraries to co-founding Voltron Data, Wes joins the show to chat about why the book cover of the pandas book doesn’t feature a panda, open source pitfalls to avoid, the pros and cons of hiring engineers at a non-profit, and more. Segments: (00:02:50) Guang’s complaint about the pandas book cover (…

In this episode, Kirk Marple, CEO and founder of Graphlit, shares his expertise on building efficient data integrations. Kirk breaks down his approach using relatable concepts: The "Two-Sided Funnel": This model streamlines data flow by converting various data sources into a standard format before distributing it. Universal Data Streams: Kirk expla…

In our latest episode, we sit down with Derek Tu, Founder and CEO of Carbon, a cutting-edge ETL tool designed specifically for large language models (LLMs). Carbon is streamlining AI development by providing a platform for integrating unstructured data from various sources, enabling businesses to build innovative AI applications more efficiently wh…

From creating Envoy to co-founding bitdrift to reimagine mobile observability, Matt joins the show to chat about being told to simply “write some proxy in Python” in the early days of building Envoy, early influences from building “shrink wrap” software at Microsoft, the process of spinning bitdrift out of Lyft, and much more. Segments: (00:03:10) …

In this episode, Nicolay sits down with Hugo Lu, founder and CEO of Orchestra, a modern data orchestration platform. As data pipelines and analytics workflows become increasingly complex, spanning multiple teams, tools and cloud services, the need for unified orchestration and visibility has never been greater. Orchestra is a serverless data orches…

From being a distinguished engineer at Sun Microsystems to co-founding Oxide Computer Company to build a new kind of server, Bryan joins the show to chat about being told that he’s on a suicide mission when starting Oxide, the moment he felt “I’m actually living HBO Silicon Valley”, and lessons from Sun. And much more. Chapters: (00:02:24) The Orig…

Ready for a three hour episode? Because the Savage FINcast has got three hour episode for ya. Craig, Raven, Jim, and Mark peel back the cover of Savage Dragon 270 to witness the aftermath of last issue. With Walter is on the run, Mickey lurking in the shadows, and Frank is slumming it in Dimension X this issue has got more plot threads then you can…

Ever wondered how AI systems handle images and videos, or how they make lightning-fast recommendations? Tune in as Nicolay chats with Zain Hassan, an expert in vector databases from Weaviate. They break down complex topics like quantization, multi-vector search, and the potential of multimodal search, making them accessible for all listeners. Zain …

From writing the first lines of Kafka over a Christmas break as a LinkedIn engineer to running a public company as the CEO of Confluent, Jay joins the show to chat about how he and his co-founders convinced investors to take a chance on their vision, what many engineers get wrong about communication, and why engineers can make great CEOs - even whe…

The bro is back in town! Matthew flew into town so we could do some podcasting. Today we got together with Dad. Some of the things we talked about were O.J. Simpson, training for Body For Life, Matthew dating twins, and more. If you'd like to support my family and I create more content, please come visit us at Patreon. patreon.com/dogbo Support the…

In this episode of "How AI is Built", data architect Anjan Banerjee provides an in-depth look at the world of data architecture and building complex AI and data systems. Anjan breaks down the basics using simple analogies, explaining how data architecture involves sorting, cleaning, and painting a picture with data, much like organizing Lego bricks…

Jorrit Sandbrink, a data engineer specializing on open table formats, discusses the advantages of decoupling storage and compute, the importance of choosing the right table format, and strategies for optimizing your data pipelines. This episode is full of practical advice for anyone looking to build a high-performance data analytics platform. Lake …

If you’ve worked on data problems, you probably have heard of Airflow and Superset, two powerful tools that have cemented their place in the data ecosystem. Building successful open-source software is no easy feat, and even fewer engineers have done this back to back. In part 2 of the conversation, we talk about Max’s journey in open source. Segmen…

Kirk Marple, CEO and founder of Graphlit, discusses the evolution of his company from a data cataloging tool to an platform designed for ETL (Extract, Transform, Load) and knowledge retrieval for Large Language Models (LLMs). Graphlit empowers users to build custom applications on top of its API that go beyond naive RAG. Key Points: Knowledge Graph…

This is a special crosspost episode where Adam Gleave is interviewed by Nathan Labenz from the Cognitive Revolution. At the end I also have a discussion with Nathan Labenz about his takes on AI. Adam Gleave is the founder of Far AI, and with Nathan they discuss finding vulnerabilities in GPT-4's fine-tuning and Assistant PIs, Far AI's work exposing…

From Problem to Requirements to Architecture. In this episode, Nicolay Gerold and Jon Erich Kemi Warghed discuss the landscape of data engineering, sharing insights on selecting the right tools, implementing effective data governance, and leveraging powerful concepts like software-defined assets. They discuss the challenges of keeping up with the e…

If you’ve worked on data problems, you probably have heard of Airflow and Superset, two powerful tools that have cemented their place in the data ecosystem. Building successful open-source software is no easy feat, and even fewer engineers have done this back to back. In Part 1 of this conversation, we chat about how to adapt to the LLM-age as engi…

In this episode, Nicolay Gerold interviews John Wessel, the founder of Agreeable Data, about data orchestration. They discuss the evolution of data orchestration tools, the popularity of Apache Airflow, the crowded market of orchestration tools, and the key problem that orchestrators solve. They also explore the components of a data orchestrator, t…

In this episode of "How AI is Built", we learn how to build and evaluate real-world language model applications with Shahul and Jithin, creators of Ragas. Ragas is a powerful open-source library that helps developers test, evaluate, and fine-tune Retrieval Augmented Generation (RAG) applications, streamlining their path to production readiness. Mai…

Out of thousands of engineers at Uber, there’s only a handful of Distinguished Engineers and Joakim was one of them. In this conversation we chat about Why software engineering is a lot like a sausage factory. Considerations for leaving big tech for a startup. “How to beat the promo commitee”. How can one effectively shape engineering culture? “Men…

In this episode of Changelog, Weston Pace dives into the latest updates to LanceDB, an open-source vector database and file format. Lance's new V2 file format redefines the traditional notion of columnar storage, allowing for more efficient handling of large multimodal datasets like images and embeddings. Weston discusses the goals driving LanceDB'…

Had a fantastic conversation with Christopher Williams, Solutions Architect at Supabase, about setting up Postgres the right way for AI. We dug deep into Supabase, exploring: Core components and how they power real-time AI solutions Optimizing Postgres for AI workloads The magic of PG Vector and other key extensions Supabase’s future and exciting n…

Its a moderately tardy episode of the Savage FINcast! Hosts Jim, Craig, Raven, and Mark take a look at Savage Dragon 269, where not even a singular 69 occurs. Malcolm and the new SOS is acclimating to San Fran life. But something fishy is going on down. And possibly something Mickey as well. All this, and Erik Larsen news, listener letters, and FIN…

If you've ever wanted a simpler way to integrate AI directly into your database, SuperDuperDB might be the answer. SuperDuperDB lets you easily apply AI processes to your data while keeping everything up-to-date with real-time calculations. It works with various databases and aims to make AI development less of a headache. In this podcast, we explo…

Supabase just acquired OrioleDB, a storage engine for PostgreSQL. Oriole gets creative with MVCC! It uses an UNDO log rather than keeping multiple versions of an entire data row (tuple). This means when you update data, Oriole tracks the changes needed to "undo" the update if necessary. Think of this like the "undo" function in a text editor. Inste…

We’re super excited to have Kelsey back on the show! Our last conversation was around his incredible career journey - from working at McDonald’s after school to starting his own computer store, to hacking on python infrastructure with the core developers, to meeting Satya Nadella for an interview. In part two of this conversation, we dive deep into…

Today’s guest is Antonio Bustamante, a serial entrepreneur who previously built Kite and Silo and is now working to fix bad data. He is building bem, the data tool to transform any data into the schema your AI and software needs. bem.ai is a data tool that focuses on transforming any data into the schema needed for AI and software. It acts as a sys…

Ethan Perez is a Research Scientist at Anthropic, where he leads a team working on developing model organisms of misalignment. Youtube: ⁠https://youtu.be/XDtDljh44DMEthan is interviewed by Mikita Balesni (Apollo Research) and Henry Sleight (Astra Fellowship)) about his approach in selecting projects for doing AI Alignment research.A transcript & wr…

Today my Dad asks me some questions about my phone and wallet being stolen recently and about my 18 year old cat Hendrix. We also talk about encouraging strangers at the gym and persevering through tough circumstances. If you'd like to support my family and I create more content, please come visit us at Patreon. patreon.com/dogbo Support the Show.…

Imagine a world where data bottlenecks, slow data loaders, or memory issues on the VM don't hold back machine learning. Machine learning and AI success depends on the speed you can iterate. LanceDB is here to to enable fast experiments on top of terabytes of unstructured data. It is the database for AI. Dive with us into how LanceDB was built, what…

We’re super excited to have Kelsey back on the show! Our last conversation was around his incredible career journey - from working at McDonald’s after school to starting his own computer store, to hacking on python infrastructure with the core developers, to meeting Satya Nadella for an interview. In part one of this conversation, we dive deep into…

Today Pops and I talk about faith, grace, will, and how different couples process things emotionally. If you'd like to support my family and I create more content, please come visit us at Patreon. patreon.com/dogbo Support the Show.By Mark Castleman McClanahan

As a self-described “gainfully unemployed data person”, Josh Wills is an angel investor and has worked on and led data teams at Slack, Cloudera, WeaveGrid and Google. We discuss: How to get started with angel investing without a ton of $$ Attributes that define great engineering managers What’s it like transitioning from management back to IC Chall…