We are at GenAI saturation, so let’s talk about scikit-learn, a long time favorite for data scientists building classifiers, time series analyzers, dimensionality reducers, and more! Scikit-learn is deployed across industry and driving a significant portion of the “AI” that is actually in production. :probabl is a new kind of company that is stewarding this project along with a variety of other open source projects. Yann Lechelle and Guillaume Lemaitre share some of the vision behind the company and talk about the future of scikit-learn!

We’re talking with Emma Bostian about going from zero to thought leader in 6 months. We talk about the nuances of UX including the differences between an UX Designer and a UX Engineer, we touch on “the great divide”, and we talk about Coding Coach — the open source project and community that Emma and others are building to connect software developers and mentors all over the world.

HashiCorp adopts a Business Source license, Matt Rickard hypothesizes why Tailwind CSS won, WarpStream sets out to make a Kafka-compatible offering directly on S3, Vadim Kravcenko publishes an excellent guide for managing difficult software engineers & Russ Cox gives an update on Go 2.

Mat Ryer is back and he’s brought with him 10 tips to be a 10x developer (like he is). After that, we try a new segment we’re calling “Tool Time” (and try out a few jingles for it along the way). Finally, it’s time to review our previous unpopular opinions and put some new ones into the world for your (dis)agreeing pleasure. Join us for an automagical time!

It seems like all we hear about are the great use cases for GenAI, but where should you NOT be using the technology? On this episode Chris and Daniel share their hot takes and bad use cases. Some may surprise you!

It can be frustrating to get an AI application working amazingly well 80% of the time and failing miserably the other 20%. How can you close the gap and create something that you rely on? Chris and Daniel talk through this process, behavior testing, and the flow from prototype to production in this episode. They also talk a bit about the apparent slow down in the release of frontier models.

José Valim joins Jerod to talk all about what’s new in Livebook – the Elixir-based interactive code notebook he’s been working on the last few years.

José made a big bet when he decided to bring machine learning to Elixir. That bet is now paying off with amazing new capabilities such as building and deploying a Whisper-based chat app to Hugging Face in just 15 minutes.

José demoed that and much more during Livebook’s first-ever launch week. Let’s get into it.

Adam and Jerod talk with Angie Byron, a core contributor and staple of the Drupal community. We haven’t covered Drupal really (sorry about that), but the call with Angie was inspiring! From the background, to the tech, the usage of the software, the communication at all levels of the community — Drupal is doing something SO RIGHT, and we’re happy to celebrate with them as they march on to the “Framlication” beat of their own drum.

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.

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.

The dataset wars are heating up, Bark is a transformer-based text-to-audio model that can generate highly realistic, multilingual speech as well as other audio, Kent Beck needs to recalibrate after using ChatGPT, the team behind Stable Diffusion release a new open source language model & Mitchel Hashimoto weighs in on prompt engineering.

At the recent ODSC East conference, Daniel got a chance to sit down with Erin Mikail Staples to discuss the process of gathering human feedback and creating an instruction tuned Large Language Models (LLM). They also chatted about the importance of open data and practical tooling for data annotation and fine-tuning. Do you want to create your own custom generative AI models? This is the episode for you!

We’re back in NYC at Microsoft Connect(); talking about the backstory of Visual Studio Code with Julia Liuson (Corporate Vice President of Visual Studio), Chris Dias (Principal Program Manager of Visual Studio and .NET), and PJ Meyer (Product Manager).

We talk about the beginnings of the Visual Studio product line, how Microsoft missed the internet, how the community is judging Microsoft and looking at them with a very old lense, how Visual Studio Code evolved from lessons learned with their cloud based editor called Monaco, how they had to radically change to reach developers beyond Windows, and how this open source project is thriving.

We’re joined by Jim Haughwout (Head of Infrastructure and Operations) and Stefan Ålund (Principal Product Manager) from Spotify to talk about how they manage hundreds of teams producing code and shipping at scale. Thanks to their recently open sourced open platform for building developer portals called Backstage, Spotify is able to keep engineering squads connected and shipping high-quality code quickly — without compromising autonomy.

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!

Dinis Cruz drops by to chat about cybersecurity for generative AI and large language models. In addition to discussing The Cyber Boardroom, Dinis also delves into cybersecurity efforts at OWASP and that organization’s Top 10 for LLMs and Generative AI Apps.

As Argilla puts it: “Data quality is what makes or breaks AI.” However, what exactly does this mean and how can AI team probably collaborate with domain experts towards improved data quality? David Berenstein & Ben Burtenshaw, who are building Argilla & Distilabel at Hugging Face, join us to dig into these topics along with synthetic data generation & AI-generated labeling / feedback.

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.

Alice Girard Guittard finds out how much she could you really get out of a $4 VPS, Brett Cannon wonders if using TOML for .env files is a good idea, Nic Mulvaney details how they count unique visitors to a website without using cookies, UIDS, or fingerprinting, after a few months, Chris Coyier is still using the Arc browser & Alex Kladov pens a love letter to Deno.

This week we’re talking with Ben Johnson. Ben is known for his work on BoltDB, his work in open source, and as a freelance Go developer. Late January when Ben open sourced his newest project Litestream in the readme he shared how the project was open source, but not open for contribution. His reason was to protect his mental health and the long term viability of the project. On this episode we talk with Ben about what that means, his thoughts on mental health and burnout in open source, choosing a license, and the details behind Litestream - a standalone streaming replication tool for SQLite.

Dalai is the simplest way to run LLaMA on your local machine, simple web tools that just work without annoying you, Wik is a tool to view wikipedia pages from your terminal, Rspack is a fast, Rust-based web bundler, Doodle is a pure Kotlin UI framework, Marqo is tensor search for humans & iLLA is an open source alternative to Retool.

This week we’re talking about Passkeys with Anna Pobletts, Head of Passwordless, at 1Password. Will Passkeys enable a passwordless future? Time will tell. Anna shares the what, the why, how, and the when on Passkeys.

We’re talking with Victor Zhou about the explosion of the .io game genre. We talked through all the details around building and running one of these games, the details behind Victor’s super popular game called Generals — which he eventually sold, and we also covered the economics behind creating and selling one of these games.

Jon Thornton (Engineering Manager at Squarespace) joined the show to talk about tech debt by way of his post to the Squarespace engineering blog titled “3 Kinds of Good Tech Debt”. We talked through the concept of “good tech debt,” how to leverage it, how to manage it, who’s in charge of it, how it’s similar to ways we leverage financial debt, and how Squarespace uses tech debt to drive product development.

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.

Taylor Troesh joins Jerod to discuss a bevy of software development topics: yak shaves, dependency selection, -10x engineers, IKEA-oriented development, his new content-addressable programming language & much more along the way.

Homebrew project leader Mike McQuaid joins us to weigh in on Apple’s big Vision Pro announcement. We also hit on our favorite (and least favorite) non-AR things from the WWDC 2023 keynote.

Christine Yen (co-founder and CEO of Honeycomb) joined the show to talk about her upcoming talk at Strange Loop titled “Observability: Superpowers for Developers.” We talk practically about observability and how it delivers on these superpowers. We also cover the biggest hurdles to observability, the cultural shifts needed in teams to implement observability, and even the gains the entire organization can enjoy when you deliver high-quality code and you’re able to respond to system failure with resilience.

This week we’re celebrating Maintainer Month along with our friends at GitHub. Open source runs the world, but who runs open source? Maintainers. Open source maintainers are behind the software we use everyday, but they don’t always have the community or support they need. That’s why we’re celebrating open source maintainers during the month of May. Today’s conversation features Alyssa Wright (Bloomberg), Chad Whitacre (Sentry), and Duane O’Brien (Creator of the FOSS Contributor Fund and framework). We get into all the details, the why, the hows, and the struggles involved for companies to support open source.

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).