Kind listens

Josh chats with Brad Axen from Block about his creation Goose as well as the Agentic AI Foundation (AAIF). I am quite skeptical of many AI claims, but Brad has a very pragmatic view about where things are today and where we might see them head. Donating Goose to the AAIF is great news as well as seeing MCP and AGENTS.MD in the foundation. We discuss how to deal with the problem of raising up junior developers, challenges of AI PRs, and some thoughts on how to get started if you're interested in AI development. The show notes and blog post for this episode can be found at

Josh chats with Brad Axen from Block about his creation Goose as well as the Agentic AI Foundation (AAIF). I am quite skeptical of many AI claims, but Brad has a very pragmatic view about where things are today and where we might see them head. Donating Goose to the AAIF is great news as well as seeing MCP and AGENTS.MD in the foundation. We discuss how to deal with the problem of raising up junior developers, challenges of AI PRs, and some thoughts on how to get started if you're interested in AI development. The show notes and blog post for this episode can be found at

Gerhard is back for Kaizen 22! We're diving deep into those pesky out-of-memory errors, analyzing our new Pipedream instance status checker, and trying to figure out why someone in Asia downloads a single episode so much.

Summary:In this episode of the Overcommitted Podcast, host Bethany and co-host Brittany Ellich dive into software engineering education with Sam Rose, a developer educator at Ngrok. Sam shares his journey from software engineering to education, emphasizing his innovative approach to improving programmer productivity through visual interactive essays that simplify complex technical concepts like large language models (LLMs). He also discusses his work on prompt caching, aiming to enhance software projects by making technical knowledge more accessible to engineers and practitioners.The conversation explores Sam's unique teaching methods, focusing on visualization and interaction as key tools in software development and career growth within tech careers. Sam reflects on his transition from an engineering role to an educator, sharing insights into the challenges of this career shift, the importance of feedback, and how his personal experiences influence his work. The episode concludes with a playful segment inspired by Sam's educational approach, highlighting the integration of engineering culture with interactive learning.Tune in for an engaging discussion that blends software engineering, education, and work-life balance, offering valuable insights for anyone interested in advancing their tech career and embracing innovative learning strategies.Takeaways:"If you truly understand something and you tinker with it, the mental model you end up with should be reasonably accurate.""Don't say 25 words if you can do it in 15.""Teaching has always felt very challenging in a really privileged way."Links:Prompt caching article: https://ngrok.com/blog/prompt-caching/Bartosz Ciechanowski: https://ciechanow.ski/Load balancing article: https://samwho.dev/load-balancing/Autism diagnosis article: https://samwho.dev/blog/getting-an-autism-diagnosis/Having a baby article: https://samwho.dev/blog/having-a-baby/Write that blog article: https://writethatblog.substack.com/p/sam-rose-on-technical-blogging)The square hole girl video: https://www.youtube.com/watch?v=cUbIkNUFs-4Hosts:Overcommitted: https://overcommitted.devBethany Janos: https://github.com/bethanyj28Brittany Ellich: https://brittanyellich.com

SummaryIn this episode of the Overcommitted Podcast, hosts Jonathan, Brittany, and Erika delve into the exciting world of AI agents. They explore the potential of AI agents in software engineering, their functionality, and the challenges of building and categorizing them. The conversation also touches on the future of job searching and personal development through AI, emphasizing the need for a more personalized and effective approach to technology and learning.Takeaways- AI agents represent a new paradigm in problem-solving.- AI agents can offload cognitive tasks.- User experience with AI agents needs to be redefined.- AI agents can be tailored to specific domains for better results.- Defining success metrics is crucial when building AI agents.- Job searching processes are outdated and need innovation.- AI can assist in personal development and career growth.- Customizable search engines could enhance information retrieval.- The role of human bias in hiring processes is significant.Links⁠Building effective agents⁠Balanced Engineer NewsletterPlausible SchemesEmbedding modelsObsidian Copilot⁠⁠⁠⁠Tech book club Repo⁠⁠⁠⁠⁠Overcommitted Discord⁠⁠⁠⁠⁠⁠Hosts⁠⁠⁠⁠⁠⁠Overcommitted.devBrittany Ellich⁠⁠⁠⁠⁠⁠Eggyhead⁠Jonathan Tamsut⁠

Another week, another Kris & Matt duo episode! This week, they're talking about Go. They cover the recent generic methods proposal by Robert Griesemer, results from the 2025 Go Developer Survey, so...

Visit https://cupogo.dev/ for all the links.Using go fix to modernize Go codeEric S. Raymond's tweet about auto-converting his C code to GoEric's HomepageSkill-validatorLinkedIn, GitHub, AgentSkillReport.comcmd/vet: check for missing Err calls for bufio.Scanner and sql.Rows #17747Meetups Shay...

MeetupsHello Stuttgart, 19 FebGo 1.26 is out!Go 1.26 release party with Anton ZhiyanovGo 1.26.0-1 available from MicrosoftLighting RoundBlog: Stepping out of Front-End with Go by ElGophertransition ppc64/linux (big-endian) from ELFv1 to ELFv2 in Go 1.27Discussion: Should Go accept CLs generated...

Steve Ruiz joins us for a deep-dive on tldraw (a very good free whiteboard) and the business he's built selling SDKs that help others build very good whiteboards (and more) with tldraw's high-performance web canvas. Along the way, we discuss the excitement/fear we share about keeping our agents busy, how SDK and infra...

This week it's Kris and Matt diving into the state of hardware, security, and what local AI actually needs to work. The conversation starts with AI agent social networks and why prompt injection is...

Welcome back to Break, a Fallthrough aftershow! Kris and Matt continue the hardware and AI conversation by zooming in on the tooling. Matt calls out the AI hype cycle of

Amal Hussein returns to tell us all about her new role at Istari, what life is like outside the web browser, how she's helping ambitious orgs in aerospace, what the SDLC looks like in 2026, and a whole lot more. Wait, moon vacuums?!

Our ol' friend, Brett Cannon, is back to talk all things Python. But first! Star Wars, Machete Order, Lost, Babylon 5, Game of Thrones, Murderbot, Ted Lasso, Project Hail Mary, David Attenborough, perpetual voice rights, and the AI uncanny valley.

Paul Dix joins us to discuss the InfluxDB co-founder's journey adapting to an agentic world. Paul sent his AI coding agents on various real-world side quests and shares all his findings: what's going to prod, what's not, and why he's (at least for a bit) back to coding by hand.

Go 1.25.7 and 1.24.13 releasedUUIDs in the standard library?crypto/uuid: add API to generate and parse UUIDscrypto/rand: add UUIDv4 and UUIDv7 generatorsThe most popular Go dependency is...Lightning roundRust vs Go in 2026 by John ArundelWelcome to Gas Town by Steve YeggeInterview with Jakub...

Welcome back to Break, a Fallthrough aftershow! Kris, Matt, and Steve pick up where the main episode left off, asking whether copyright actually matters to working developers. Kris draws parallels ...

This week Steve's back to tackle the big question: is AI-generated output copyrightable? The conversation includes discussions of the Copyright Act of 1976, the philosophy of why copyright exists a...

Mike McQuaid, Project Leader of Homebrew, joins Corey Quinn to share how a package manager conceived in a London pub became essential for 10 million Mac users. Homebrew lets you install software with one command instead of downloading files and clicking through installers, maintained by just 30...

Listen now (114 mins) | How Peter Steinberger, creator of OpenClaw (formerly: Clawd), builds and ships like a full team by centering his development workflow around AI agents.

In May of 2025, Docker launched Hardened Images, a secure, minimal, production-ready set of images. In December, they made DHI freely available and open source to everyone who builds software. On this episode, we're joined by Tushar Jain, EVP of Engineering at Docker to learn all about it.

Visual Studio Code has become one of the most influential tools in modern software development. The open-source code editor has evolved into a platform used by millions of developers around the world, and it has reshaped expectations for what a modern development environment can be through its intuitive UX, rich extension marketplace, and deep integration

This week the crew chats with Hirsch Singhal, Staff Product Manager at GitHub, about effective collaboration between product and engineering. LinksHirsch Singhal's Bluesky: https://bsky.app/profile/hpsin.netHirsch Singhal's LinkedIn: https://www.linkedin.com/in/hirsch-singhal/Domain-Driven Design: https://www.amazon.com/Domain-Driven-Design-Tackling-Complexity-Software/dp/0321125215 Hosts⁠⁠⁠⁠Overcommitted.dev⁠⁠⁠⁠Bethany Janos: ⁠⁠⁠⁠https://github.com/bethanyj28⁠⁠⁠⁠Brittany Ellich: ⁠⁠⁠⁠https://brittanyellich.com⁠⁠⁠⁠Eggyhead: ⁠⁠⁠⁠https://github.com/eggyhead⁠⁠⁠Jonathan Tamsut: ⁠⁠https://jtamsut.substack.com⁠⁠

What's in the SOSS? features the sharpest minds in security as they dig into the challenges and opportunities that create a recipe for success in making software more secure. Get a taste of all the ingredients that make up secure open source ...

Welcome back to Break, a Fallthrough aftershow! It's just Kris and Steve for this one! After brief reflections on the Gastown discussion, the episode pivots into a deep dive on semantic versioning,...

This week we're talking about Gastown! Dylan and Steve join Kris to break down the viral project that spins up hundreds of Claude Code instances to build a software factory. Steve makes the case fo...

Techno Tim joins Adam to dive deep into the state of homelab'ing in 2026. Hardware is scarce and expensive due to the AI gold rush, but software has never been better. From unleashing Claude on your UDM Pro to building custom Proxmox CLIs, they explores how AI is transforming what's possible in the homelab. Tim declare...

We discuss the buzz around Clawdbot / MoltBot / OpenClaw, how app subscriptions are turning into weekend hacking projects, why SaaS stocks are crashing on Wall Street, and what it all means.

AI coding agents are rapidly reshaping how software is built, reviewed, and maintained. As large language model capabilities continue to increase, the bottleneck in software development is shifting away from code generation toward planning, review, deployment, and coordination. This shift is driving a new class of agentic systems that operate inside constrained environments, reason over

As the creator and long-time maintainer of ESLint, Nicholas Zakas is well-positioned to criticize GitHub's recent response to npm's insecurity. He found the response insufficient, and has other ideas on how GitHub could secure npm better. On this episode, Nicholas details these ideas, paints a bleak picture of npm alte...

ProposalsAccepted: direct reference to embedded fields in struct literalsNew: Generic Methods for Go

Quinn and Thorsten are back! It's been a while since they published a Raising An Agent episode and in this this episode, they discuss how everything seems to have changed again with Gemini 3 and Opus 4.5 and what comes after — the assistant is dead, long live the factory.

In this episode of Raising an Agent, Beyang and Camden dive into how the Amp team evaluates models for agentic coding. They break down why tool calling is the key differentiator, what went wrong with Gemini Pro, and why open models like K2 and Qwen are promising but not ready as main drivers. They share first impressions of GPT-5, explore the idea of alloying models, and explain why qualitative “vibe checks” often matter more than benchmarks. If you want to understand how Amp thinks about model selection, subagents, and the future of coding with agents, this episode has you covered.

In this episode, Beyang and Thorsten discuss strategies for effective agentic coding, including the 101 of how it's different from coding with chat LLMs, the key constraint of the context window, how and where subagents can help, and the new oracle subagent which combines multiple LLMs. 00:53 Intros 03:35 How coding with agents is very different from coding with prior AI tools that use chat LLMs 10:46 Example of an agentic coding run to fix a simple issue 14:28 Example of debugging an issue with an MCP server 22:05 Example of unifying two build scripts that share logic 25:24 How context window size has emerged as a key constraint on agentic automation 31:16 Why it's best to focus on one thing at a time per agentic thread 33:24 Subagents and how they help extend the effective context window 34:04 The Amp codebase search subagent 38:48 General-purpose subagents 44:20 When to use subagents 47:04 The oracle subagent and o3 51:47 Multi-model agents and using the best model for each job

In this episode, Quinn and Thorsten discuss Claude 4, sub-agents, background agents, and they share "hot tips" for agentic coding.

In this episode, Beyang interviews Thorsten and Quinn to unpack what has happened in the world of Amp in the last five weeks: how predictions played out, how working with agents shaped how they write code, how agents are and will influence model development, and, of course, all the things that have been shipped in Amp.

Thorsten and Quinn talk about the future of programming and whether code will still be as valuable in the future, how maybe the GitHub contribution graph is already worthless, how LLMs can free us from the tyranny of input boxes, and how conversations with an agent might be a better record of how a code change came to be than git commit tools. They also share where it works and simply doesn't work.

Quinn and Thorsten start by sharing how reviews are still very much needed when using AI to code and how it changes the overall flow you're in when coding with an agent. They also talk about a very important question they face: how important is code search, in its current form, in the age of AI agents?

Thorsten and Quinn talk about how different agentic programming is from normal programming and how the mindset has to adapt to it. One thing they discuss is that having a higher-level architectural understanding is still very important, so that the agent can fill in the blanks. They also talk about how, surprisingly, the models are really, really good when they have inputs that a human would normally get. Most importantly, they share the realization that subscription-based pricing might make bad agentic products.

In the first episode of Raising an Agent, Quinn and Thorsten kick things off by sharing a lot of wow-moments they experienced after getting the agent at the heart of Amp into a working state. They talk about how little is actually needed to create an agent and how magical the results are when you give a model the right tools, unlimited tokens, and feedback. That might be the biggest surprise: how many previous assumptions feel outdated when you see an agent explore a codebase on its own.

The crew gets philosophical about the ethics of building Artificial Intelligence systems. Are software engineers going to be replaced? Is it ethical to build AI systems?Links⁠SuperintelligenceBlog: Less WrongZizian cultThinking in SystemsDwarkesh Patel podChatGPT Medical Diagnosis StudyMCP Server Claude Desktop TutorialMCP Podcast⁠Overcommitted on Bluesky⁠Hosts⁠Overcommitted.dev⁠Brittany Ellich: ⁠https://brittanyellich.com⁠Eggyhead: ⁠https://github.com/eggyhead⁠Jonathan Tamsut: ⁠https://jtamsut.substack.com⁠

The crew chat about our experience using AI right now as software engineers (which is subject to change even by the time this episode airs). Including an overview of our current thoughts on the AI landscape, what tools we use for which tasks, and our thoughts on what we are excited about for the future!LinksThe S in MCP Stands for SecurityBook: The Scaling EraOvercommitted on BlueskyHostsOvercommitted.devBethany Janos: https://github.com/bethanyj28Brittany Ellich: https://brittanyellich.comEggyhead: https://github.com/eggyheadJonathan Tamsut: https://jtamsut.substack.com

Welcome back to Break, a Fallthrough aftershow! In this episode, Kris, Matt, and Steve talk about Fallthrough episode #32, problems with software security, why privacy is important, and so much mor...

In the years leading up to the current AI hype cycle we're currently all experiencing, there was another hype cycle: Big Data. In this episode, Kris is joined by Matt and Steve to discuss how the B...

Package management sits at the foundation of modern software development, quietly powering nearly every software project in the world. Tools like npm and Yarn have long been the core of the JavaScript ecosystem, enabling developers to install, update, and share code with ease. But as projects grow larger and the ecosystem more complex, this older

Damien Tanner (founder of Pusher, now building Layercode) is back for a reunion 17 years in the making. Damien officially returns to The Changelog to discuss the seismic shift happening in software development. From the first sponsor of the podcast to frontline builder in the AI agent era, Damien shares his insights on...