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...

GopherJS 1.20 releasedListen to interview with Grant Nelson, Episode 53Results from the 2025 Go Developer SurveyInterview with Dominic St-Pierrego podcast()StaticBackendDominic on LinkedIn

Welcome back to Break, a Fallthrough aftershow! In this episode, Annie and Michael Hedgepeth stick around for Break. The panel kicks off with Michael's anxiety about his

Annie and Michael Hedgpeth, founders of People Work, join Kris and Matt to unpack the junior hiring crisis and what's really broken about how we grow engineers. Annie's viral blog post sparked deba...

AI isn’t here to save you from your codebase. Brittany Ellich explains how to use it to maintain what already works… without chasing rewrite fantasies or shipping chaos.

Want to share our last week's episode? Here is the link!Want to send a voice note for our 3 year episode? Here!News[security] Go 1.26 Release Candidate 2 is released[security] Go 1.25.6 and Go 1.24.12 are releasedGophercamp 2026Lightning RoundHow to Get Consistent Classification From Inconsistent...

Time for the annual predictions episode! Bryan and Adam were joined by frequent future-ologists Simon Willison, Steve Klabnik, and Ian Grunert to review past predictions and peer into the future. If any of these predictions come to fruition, it's going to be an interest 1, 3, or 6 years!In...

What do LLMs mean for the future of software engineering? Will vibe-coded AI slop be the norm? Will software engineers simply be less in-demand? Rain and David join Bryan and Adam to discuss how rigorous use of LLMs can make for much more robust systems.In addition to Bryan Cantrill and Adam...