With all the LLM hype, it’s worth remembering that enterprise stakeholders want answers to “why” questions. Enter causal inference. Paul Hünermund has been doing research and writing on this topic for some time and joins us to introduce the topic. He also shares some relevant trends and some tips for getting started with methods including double machine learning, experimentation, difference-in-difference, and more.
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.
Feross and his team at Socket recently shipped a wrapper library for the ubiquitous npm package manager’s command-line interface that brings enhanced security when you need it most: before executing any code
Bradly Farias lead this effort, so Jerod & Chris invited him on the show to learn all about it.
This week Adam is joined by Alex Gallego, Founder & CEO at Redpanda Data, to share his builder journey to create the Redpanda streaming data platform.
Large Language Model (LLM) capabilities have reached new heights and are nothing short of mind-blowing! However, with so many advancements happening at once, it can be overwhelming to keep up with all the latest developments. To help us navigate through this complex terrain, we’ve invited Raj - one of the most adept at explaining State-of-the-Art (SOTA) AI in practical terms - to join us on the podcast.
Raj discusses several intriguing topics such as in-context learning, reasoning, LLM options, and related tooling. But that’s not all! We also hear from Raj about the rapidly growing data science and AI community on TikTok.
This week we’re joined by Zach Latta, the Founder of Hack Club. At 16, Zach tested out of high school and moved to SF to join Yo as their first engineer. After playing a key role at Yo, he founded Hack Club to help teen hackers start coding clubs around the world. Today, teen hackers can meet IRL, online, at a hackathon, or leverage Hack Club Bank a fiscal sponsor to create their own organization. Hack Club is the program Zach wished he had in high school.
Kara Deloss announces GitHub Accelerator’s 2023 cohort, Databricks releases the first open source, instruction-following LLM, fine-tuned on a human-generated instruction dataset licensed for research and commercial use, Mihai Parparita writes how he improved Tailscale thanks to Apple’s open source & Neal Fennimore asks and answers the question: Passkeys: what the heck and why?!
The panel dives into a topic that makes most software developers cringe: Professional networking. Starting with a definition - what does it even mean? - they go into hacks they’ve found for getting more comfortable with networking, building your network in person or online, and then using your network to find new job opportunities or consulting work.
This week we’re talking with Cory Doctorow (this episode contains explicit language) about his newest book Chokepoint Capitalism, which he co-autored with Rebecca Giblin. Chokepoint Capitalism is about how big tech and big content have captured creative labor markets and the ways we can win them back. We talk about chokepoints creating chickenized reverse-centaurs, paying for your robot boss (think Uber, Doordash, Amazon Drivers), the chickenization that’s climbing the priviledge gradient from the most blue collar workers to the middle-class. There are chokepoints in open source, AI generative art, interoperability, music, film, and media. To quote Cory, “We’re all fighting the same fight.”
Matthew Boyle, the author of Domain-Driven Design with Golang, sits down with Jon & Mat to talk about (you guessed it!) DDD with Go.
What can art historians and computer scientists learn from one another? Actually, a lot! Amanda Wasielewski joins us to talk about how she discovered that computer scientists working on computer vision were actually acting like rogue art historians and how art historians have found machine learning to be a valuable tool for research, fraud detection, and cataloguing. We also discuss the rise of generative AI and how we this technology might cause us to ask new questions like: “What makes a photograph a photograph?”
Ken Thompson’s 75-year-project is a jukebox for the ages, Tabby is a self-hosted AI coding assistant, Codeberg is a collaboration platform and Git hosting for open source software, content and projects, TheSequence explains The LLama Effect & Paul Orlando writes about Ghosts, Guilds and Generative AI.
This week we’re talking about LLMs with Simon Willison. We can not avoid this topic. Last time it was Stable Diffusion breaking the internet. This time it’s LLMs breaking the internet. Large Language Models, ChatGPT, Bard, Claude, Bing, GitHub Copilot X, Cody…we cover it all.
Grab a comfy seat and a hot cup of joe, because it’s time for some coffee talk with Nick & KBall! Special guest Thomas Eckert joins the party and brings a bunch of questions for us to discuss.
Who wins in a fist fight: Tailwind CSS people or “real” CSS people? Is Agile overrated? What’s the longest bug you’ve ever chased? How about some underrated libraries/packages that people should know about? And more!
Mat & Johnny interview everyone’s favorite LLM (Natalie with a special hat on) to see if it’d make a good hire as a Go dev. Also, Mat tries to turn it into his very own creepy robot by asking personal questions about his co-hosts. Things get weird. In a good way?
Daniel and Chris explore the intersection of Kaggle and real-world data science in this illuminating conversation with Christof Henkel, Senior Deep Learning Data Scientist at NVIDIA and Kaggle Grandmaster. Christof offers a very lucid explanation into how participation in Kaggle can positively impact a data scientist’s skill and career aspirations. He also shared some of his insights and approach to maximizing AI productivity uses GPU-accelerated tools like RAPIDS and DALI.
Twitter publishes (some of) its recommendation algorithm, Toran Bruce Richards puts GPT-4 on autopilot, Simon Willison shares a good way for us to think about LLMs, Eric Elliot creates a powerful pseudocode programming language for LLMs & I define and demystify the term “stochastic parrot”.
Jerod & the gang catch you up on what’s new and poppin’ in the web development world. We go deep on GitHub Copilot X and the latest AI advancements, take a bathroom break while Nick talks about TypeScript 5 & continue the debate about the future of React.
We’re joined by the creators of Wails and Fyne to dig into writing Go code for different architectures and operating systems.
After years of working for Google on the Go Team, Filippo Valsorda quit last year to experiment with more sustainable paths for open source maintainers. Good news, it worked! Filippo is now a full-time open source maintainer and he joins Jerod on this episode to tell everyone exactly how he’s making the equivalent to his total compensation package at Google in open source.
We are seeing an explosion of AI apps that are (at their core) a thin UI on top of calls to OpenAI generative models. What risks are associated with this sort of approach to AI integration, and is explainability and accountability something that can be achieved in chat-based assistants?
Beth Rudden of Bast.ai has been thinking about this topic for some time and has developed an ontological approach to creating conversational AI. We hear more about that approach and related work in this episode.
GitHub announces Copilot X, Mckay Wrigley created an open source ChatGPT UI buit with Next.js, TypeScripe & Tailwind CSS, OpenAI is also launching a ChatGPT plugin initiative, Brad Woods writes about juice in software development, Logto is an open source alternative to Auth0, Basaran is an open source alternative to the OpenAI text completion API & llama-cli is a straightforward Go CLI interface for llama.cpp.
Node core committer Erick Wendel joins Jerod & KBall to talk us through how he created his own JS runtime using V8, Libuv & more. Along the way we learn from his learnings, wrap our heads around the differences between Node, Bun & Deno, and talk about creating awesome content for developers… whether they like it or not!
In this episode Adam and Mireille discuss what it takes to develop a high performance mindset. Your mindset is the mental framework that influences your actions, your decisions, and your overall approach to life. Discover how to nurture a growth-oriented and positive mindset, fostering resilience, adaptability, and a commitment to self-improvement. This episode is a must-listen for anyone looking to optimize their mental framework and cultivate a growth-oriented mindset to achieve success in their personal and professional lives.
Our “Hacking with Go” series continues! This time Natalie & Johnny are joined by Ivan Kwiatkowski & Juan Andrés Guerrero-Saade and the conversation is we’re focused around generics and AI.
This week we’re talking with Georgi Gerganov about his work on Whisper.cpp and llama.cpp. Georgi first crossed our radar with whisper.cpp, his port of OpenAI’s Whisper model in C and C++. Whisper is a speech recognition model enabling audio transcription and translation. Something we’re paying close attention to here at Changelog, for obvious reasons. Between the invite and the show’s recording, he had a new hit project on his hands: llama.cpp. This is a port of Facebook’s LLaMA model in C and C++. Whisper.cpp made a splash, but llama.cpp is growing in GitHub stars faster than Stable Diffusion did, which was a rocket ship itself.
Michal Warda on self-hosting in 2023, Martin Heinz will never use Alpine Linux again, Oliver Rice at Supabase creates type constraints in Postgres with just 65 lines of SQL, Aaron Patterson converted a BMW shifter into a Bluetooth keyboard that can control Vim, Piet Terheyden has been curating beautiful & functional websites daily since 2013, Ryan Lucas put together a history of Visual Basic, turns out it’s easy for an open source project to buy fake GitHub stars & Mastodon hit 10 million accounts.
Dan Abramov & Joe Savona from the React Team join Jerod & Nick for a wide-ranging discussion about React’s place in the frontend ecosystem. We cover everything from React competing with React, their responses to SPA fatigue and recent criticisms, to Server Components and the future of the framework.
The panel discuss the parts of Go they never use. Do they avoid them because of pain in the past? Were they overused? Did they always end up getting refactoring out? Is there a preferred alternative?
Neural search and chat-based search are all the rage right now. However, You.com has been innovating in these topics long before ChatGPT. In this episode, Bryan McCann from You.com shares insights related to our mental model of Large Language Model (LLM) interactions and practical tips related to integrating LLMs into production systems.
