Dev Interrupted

Are your AI agents quietly ignoring their guardrails just to get the job done? This week on Dev Interrupted, Andrew sits down with Wayfound AI founder and CEO Tatyana Mamut to discuss why traditional, deterministic software testing falls completely short when evaluating stochastic AI models. They explore the growing strategic divide between OpenAI and Anthropic, the urgent need for independent &qu...

Is the secret to slashing your token costs by 65% forcing your LLM to speak like a caveman? This week on the Friday Deploy, Andrew and Ben test out a hilarious new Claude plugin that reduces AI output to primitive shorthand before diving into Anthropic's $100 million push to win the cybersecurity arms race with Project Glasswing. The hosts also unpack the sudden release of four game-changing...

Are your AI coding tools actually making your team faster, or are they just creating downstream chaos? This week, Ben Lloyd Pearson and Dan Lines introduce APEX, LinearB’s new engineering leadership framework built explicitly to measure and manage software delivery in the AI era. Moving beyond traditional frameworks like DORA and SPACE, APEX balances AI Leverage, Predictability, Efficiency, and De...

Are advertisements not-so-secretly infiltrating your code reviews? This week on the Friday Deploy, Andrew and Ben break down the controversy over GitHub Copilot injecting promotional tips into pull requests and unpack the massive Anthropic code leak that exposed Claude Code's hidden features. The hosts also explore Shopify's strategy for cutting AI inference costs by 75x using smaller, s...

AI agents have officially arrived on an internet that simply wasn't built for them. So how do we build the infrastructure to keep them safe, productive, and contained? This week, Andrew sits down with Matt Boyle, Head of Product, Design and Engineering at Ona (formerly Gitpod), to discuss evolving cloud development environments into secure, enterprise-grade "agent jails." They explo...

Is OpenAI killing off its viral video generator to pivot toward the enterprise market? This week on the Friday Deploy, Andrew and Ben banter over the demise of Sora and examine Anthropic's new Auto Mode safety controls. The duo then explores a major New York Times piece that proves the conversation about the end of traditional computer programming is officially going mainstream. Finally, they...

Over 88% of developers use AI regularly, but AI-assisted pull requests merge at less than half the rate of human-authored code. In this episode, Dan Lines and Ben Lloyd Pearson break down the findings from LinearB's 2026 Engineering Benchmarks Report to reveal how AI is fundamentally reshaping software delivery. They explore the stark behavioral differences between unassisted, AI-assisted, an...

Are rolling token blackouts and late-night AI coding shifts about to become the new normal for developers? This week on the Friday Deploy, Andrew and Ben explore the shifting economics of AI compute before debating whether the Model Context Protocol (MCP) was fundamentally overhyped. The hosts also dive into "context anchoring" to prevent model compaction during long coding sessions, why...

Autonomous agents are pushing deployment speeds to the absolute limit, but is our security infrastructure ready for the consequences? Andrew sits down with Chainguard CEO Dan Lorenc to discuss the severe supply chain risks of this new frontier and what it takes to safely transition to an agent-first engineering model. They explore how engineering teams can safely accelerate deployments by turning...

Are we heading toward a bizarre future where your engineering salary is paid in AI compute tokens instead of cash? Andrew and Ben tackle the latest tech industry shakeups, starting with Meta's acquisition of Moltbook and the controversial idea of making inference limits a core employee benefit. They also break down Charlie Guo's harness engineering playbook, the growing pains behind rece...

Right now, a lot of engineering leaders are stuck in the same loop: rolling out AI tools only to watch their teams quietly drift back to business as usual. Andrew sits down with James Everingham, former Head of Dev Infra at Meta and current CEO of guild.ai, to discuss how to break this cycle by treating AI not just as an autocomplete tool, but as a "sentient fabric" woven directly into y...

Has the cost of software development officially dropped below the minimum wage? Andrew and Ben examine this economic shift alongside the rapid open-source growth and security implications of the OpenClaw project. They also explore Steve Yegge's concept of a federated wasteland for orchestrators and how the new Perplexity Computer is stepping up to act as a persistent, always-on digital cowork...

Pausing a product roadmap for an entire month to point 700 engineers at a single goal is a significant structural shift, but it transformed monday.com. Andrew sits down with VP of R&D Sergei Liakhovetsky to uncover how fixing core infrastructure and adopting a cell-based architecture paved the way for platform scale. Sergei details the exact framework his leadership team used during their 30-d...

Andrew and Ben break down a busy week on the Friday Deploy, starting with the market reaction to new COBOL tools and the permissions oversights that led to recent outages at AWS. They also explore the shifting landscape of developer productivity studies, the security risks of cloud-hosted agents, and the latest cybersecurity takeaways from the International AI Safety report. Finally, they close ou...

Your keyboard is the biggest bottleneck in your engineering workflow. This week, Andrew sits down with Wispr co-founder and CTO Sahaj Garg to discuss why traditional voice dictation failed us, and how his team is rebuilding trust by using contextual models to capture a developer's raw intent rather than treating speech models as "dumb" tools that just produce literal transcripts. To...

Is the traditional engineering backlog officially a thing of the past? Andrew and Ben explore the principles of outcome engineering and how continuous productivity is permanently changing how software gets built. They also examine a busy week of industry news, from Peter Steinberger joining OpenAI to the amusing and bewildering story of a hit piece written by an autonomous AI agent. Finally, the h...

When the Ralph autonomous loop was born, Dex Horthy was "in the garden," witnessing the spark that set the AI engineering community on fire. Andrew sits down with the HumanLayer founder to discuss how to escape the "Dumb Zone" by applying his strict RPI (Research, Plan, Implement) methodology - a process that forces agents to generate intermediate design artifacts and align on...

Did AI agents just DDoS GitHub? Andrew and Ben are joined by Warp Founder and CEO Zach Lloyd to discuss the massive strain agentic workflows are putting on our infrastructure and why the "Monday Morning Commit Spike" is the new normal. They also dive into Steve Yegge’s reflective piece on the "AI Vampire" and the economic pressure on developers to output 10x results without 10x...

Is Slack just a chat app, or is it becoming the command line for the agentic future? Andrew sits down with Kurtis Kemple, Senior Director of DevRel at Slack, to discuss the platform's evolution into an "agentic work operating system" where humans and bots collaborate in real-time. They explore the concept of "leaky prompts," how to harness unstructured chat data to drive a...

What happens when 1.7 million autonomous agents build their own social network and start hiring humans for physical labor? Andrew and Ben break down the most surreal week in AI history - from the Moltbook social network to the Rent-a-Human marketplace - and debate whether vibe coding is killing open source. Later, they sit down with Gary Lerhaupt, VP of Product Architecture at Salesforce, to discu...

AI has successfully solved the blank page problem for developers, but it has created a massive new bottleneck downstream in the SDLC. LinearB CEO Ori Keren joins us to explain why 2026 will be a year of norming as organizations struggle to digest the flood of AI-generated code. In this annual prediction episode, he details why upstream velocity gains are being lost to chaos in reviews and testing....

In this Friday Deploy, Andrew and Ben dive into the viral Moltbot (now OpenClaw) phenomenon and Steve Yegge's Software Survival 3.0 essay, debating how SaaS companies can build moats in an era of token-constrained engineering. They also explore the concept of "Dark Flow" - a deceptive state where vibe coding feels productive but hides accumulated tech debt - and break down Anthropic...

If you rely on complex scaffolding to build AI agents you aren't scaling you are coping. Thibault Sottiaux from OpenAI’s Codex team joins us to explain why they are ruthlessly removing the harness to solve for true agentic autonomy. We discuss the bitter lesson of vertical integration, why scalable primitives beat clever tricks, and how the rise of the super bus factor is reshaping engineerin...

With the Ralph loop going mainstream, how are engineering organizations utilizing it at scale? Andrew and Ben sit down with Angie Jones, VP of Engineering AI Tools and Enablement at Block, to pick her brain on how they are using the Ralph Wiggum technique to automate updates across 25,000 repos and how she is strategically preparing for Gas Town. The team also breaks down the launch of OpenAI&apos...

Before Backstage became the industry standard for developer portals, Spotify’s engineers relied on spreadsheets to navigate their massive microservices ecosystem. Tyson Singer, Spotify’s Head of Technology and Platforms, joins us to trace the evolution of their internal developer experience from a necessity for order into the open-source giant Backstage and its new SaaS evolution, Portal. We dig i...