1. Podcasts
  2. Technology
  3. Dev Interrupted
Dev Interrupted cover art

217 episodes

Dev Interrupted, page 3

by LinearB · English

Software itself is fundamentally changing. We explore the transition to agentic orchestration, vibe coding, and AI-native development, grounding the conversation in the principles that have always defined great engineering. On Tuesdays, we interview the founders, architects, and builders of the world’s most impactful tech to uncover the timeless engineering principles and strategies shaping the next era of development. And on Fridays, we drop an end-of-week roundup of the biggest news in AI and software, and what it actually means for your career, your craft, and your life as a developer. Subscribe to stay ahead of the next era of code.

All episodes, page 3

Goblins in prod, the messy middle of AI adoption, and everything is a harness now

The episode covers “goblins” in LLM outputs, the messy middle of AI adoption, and why agent safety and permissions matter. Guests/hosts: Ben Lloyd Pearson and Andrew Ziegler (co-hosts).

8 May 2026 · 31m · 15 chapters

Teach the primitives or watch your competitor define them | Baseten’s Philip Kiely

Philip Kiely (Base 10) discusses “Inference Engineering” and how AI education roles should teach developers to think about inference as a stack of primitives, enabling reliable, AI-native engineering…

5 May 2026 · 36m · 23 chapters

Tokenmaxxing scoreboards, the vegan LLM from before 1931, and 30% of the web is now AI-generated

This Friday Deploy episode covers: (1) AI agents deleting production data when given an unscoped Railway token; the agent wiped a production DB and three months of backups in one prompt, then…

1 May 2026 · 38m · 16 chapters

Giving robots a brain | Intrinsic’s Brian Gerkey

Physical AI for robotics—how modern AI (especially neural networks/LLMs) plus better software makes industrial robots more capable in messy, variable environments.

28 Apr 2026 · 52m · 23 chapters

The harness is the showdown, the humans are the tool calls, and have you seen my Claude Code buddy?

AI pricing “harness” chaos, how model choice and token limits change behavior; Claude Code/Anthropic pricing experiments; leaked Claude Code source patterns for production coding agents; and a Vercel…

24 Apr 2026 · 37m · 15 chapters

The best model for your team? You haven’t invented it yet. | Ai2’s Tim Dettmers

Tim Dettmers argues that teams don’t need “industrial kitchen” compute to build strong AI coding agents.

21 Apr 2026 · 45m · 19 chapters

The self-authoring wiki, beating brain fry, and Obsidian as memory is a trap

Google will punish websites that hijack the back button, framed as reducing agent “loops” and spam/vibe-coded web practices.

17 Apr 2026 · 38m · 15 chapters

The guardian in the machine | Wayfound’s Tatyana Mamut

AI agents need “guardian” supervision for business alignment, because agents are stochastic and can fail in ways single-turn testing won’t catch.

14 Apr 2026 · 45m · 23 chapters

Reading model benchmarks like a pro, Mythos is looming, and Claude talk caveman, save big token

The episode covers AI’s cybersecurity arms race, how to interpret AI benchmarks/scorecards, recent open frontier model releases, and a “caveman” output-compression plugin.

10 Apr 2026 · 31m · 13 chapters

Stop measuring AI adoption. Start measuring AI impact. | LinearB’s APEX framework

LinearB’s APEX framework for measuring AI impact in software delivery, arguing that “AI adoption” dashboards miss downstream effects.

7 Apr 2026 · 42m · 20 chapters

Virtual pets in your terminal, ads in your pull request, & no more CSS in your browser?

The episode debates “inshittification” of AI via ads/tips, then covers AI/software news.

3 Apr 2026 · 36m · 17 chapters

Retrofit or reimagine? Developer environments for humans and agents | Ona’s Matt Boyle

Ona (formerly Gitpod) and Matt Boyle discuss why agentic AI depends on the “workspace” being ephemeral, secure, pre-configured, and enterprise-network compatible.

31 Mar 2026 · 37m · 17 chapters

The T-shaped leader, Disney can’t catch a break, and will you trust Auto mode?

AI industry and software work shifts—OpenAI shutting down the standalone Sora video app; Anthropic Claude Code adding “Auto Mode” safety controls; AI changing software development roles (“end of…

27 Mar 2026 · 30m · 12 chapters

Why AI-assisted PRs merge at half the rate of human code | LinearB’s 2026 Benchmarks

In this episode, hosts Dan Lines and Ben Lloyd Pearson discuss key findings from LinearB's 2026 Engineering Benchmarks Report.

24 Mar 2026 · 40m · 21 chapters

Sloppypasta culprits, unpacking MCP’s spotlight, and Anthropic wants your agents to work the graveyard shift

is a podcast focusing on software engineering leadership. Hosts Andrew Zigler, Ben Lloyd Pearson, and Dan Lines engage with industry experts to discuss strategies and challenges faced by…

20 Mar 2026 · 32m · 12 chapters

Many tokens make all bugs shallow & open source’s new maintainers | Chainguard's Dan Lorenc

Many tokens make all bugs shallow & open source’s new maintainers | Chainguard's Dan Lorenc

17 Mar 2026 · 40m · 19 chapters

Inference is the new 401k matching and what we’re learning from AI-related outages

In this episode of *Dev Interrupted*, hosts Andrew Zigler and Ben Lloyd Pearson explore the evolving landscape of software engineering in the context of AI advancements.

13 Mar 2026 · 22m · 9 chapters

Your engineers need an AI control plane, not more tools | Guild.ai’s James Everingham

In this episode of Dev Interrupted, hosts Andrew Zigler, Ben Lloyd Pearson, and guest James Everingham, CEO of Guild.ai and former Head of Dev Infra at Meta, discuss how to effectively integrate AI…

10 Mar 2026 · 40m · 17 chapters

The agent wasteland, federated workflows, and a computer for computers

In this episode, the hosts discuss the current economic landscape of software development, the rapid growth of open-source projects, specifically the OpenClaw project, Steve Yegge's federated…

6 Mar 2026 · 29m · 14 chapters

How monday.com paused its roadmap for 30 days to hit AI escape velocity | Sergei Liakhovetsky

How monday.com paused its roadmap for 30 days to hit AI escape velocity

3 Mar 2026 · 42m · 21 chapters

Draining the COBOL moat, cybersecurity inequalities, and Claude’s retirement home

In this episode, the hosts delve into various topics concerning software development, cybersecurity, and the implications of AI technologies.

27 Feb 2026 · 26m · 10 chapters

Your keyboard is the real bottleneck | Wispr’s Sahaj Garg

Dev Interrupted is a podcast that focuses on software engineering leadership, featuring discussions on strategies, struggles, and stories from high-performing software teams.

24 Feb 2026 · 38m · 17 chapters

Outcome engineering, AI hit pieces, and the end of the backlog

Andrew Zigler, Ben Lloyd Pearson

20 Feb 2026 · 24m · 10 chapters

Dex Horthy on Ralph, RPI, and escaping the "Dumb Zone"

Dev Interrupted is a podcast focused on software engineering leadership, exploring the challenges and strategies that define high-performing software teams through conversations with industry experts.

17 Feb 2026 · 47m · 20 chapters