Angie Jones on Ralphing 25k repos at Block, GPT-5.2 Codex, and CES weirdness

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's new GPT-5.2 Codex model before closing out the week with a look at the weirdest tech from CES, from hypersonic knives to music-playing lollipops.LinearB: Measure the impact of GitHub Copilot and CursorFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Angie Jones: angiejones.tech | LinkedIn | X (Twitter)Goose (Block’s AI Agent): github.com/block/gooseSteve Yegge’s "Welcome to Gas Town": Read on MediumGeoffrey Huntley’s Ralph Loop: ghuntley.com/ralphRyan Dahl on the End of Coding: @rough__seaThe Weirdest Tech of CES: Read the ArticleOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

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 into how they use golden paths to align autonomous squads and how their new AI Knowledge Assistant (AiKA) reduced internal support tickets by nearly 50% while protecting developer flow. Finally, Tyson shares his philosophy on sustainable innovation, explaining how to train an engineering organization to run a marathon at a sprinter's pace.LinearB: Measure the impact of GitHub Copilot and CursorFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Spotify Engineering Blog: engineering.spotify.comSpotify Portal: backstage.spotify.comConfidence: confidence.spotify.comConnect with Tyson: LinkedInOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

In our first-ever Friday edition, Andrew and Ben dive into the viral "Ralph Loop" phenomenon and discuss how simple bash loops and deterministic context allocation are changing the unit economics of code. They also explore Steve Yegge's chaotic "Gas Town" concept for orchestrating AI agents, debate whether AI is killing the individual contributor role, and share a laugh over a creepy link generator that challenges our trust in URLs. LinearB: Measure the impact of GitHub Copilot and CursorFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's stories:Cowork: Claude Code for the rest of your workGas Town Emergency User ManualLoom by Geoffrey HuntleyAI Killed the Individual ContributorCreepyLinkOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Geoffrey Huntley argues that while software development as a profession is effectively dead, software engineering is more alive—and critical—than ever before. In this episode, the creator of the viral "Ralph" agent joins us to explain how simple bash loops and deterministic context allocation are fundamentally changing the unit economics of code. We dive deep into the mechanics of managing "context rot," avoiding "compaction," and why building your own "Gas Town" of autonomous agents is the only way to survive the coming rift.LinearB: Measure the impact of GitHub Copilot and CursorFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest(s):Geoffrey’s Website & Blog: ghuntley.comBuild Your Own Coding Agent Workshop: ghuntley.com/agent Ralph Wiggum as a Software Engineer: ghuntley.com/ralphSteve Yegge’s "Welcome to Gas Town": Read on MediumThe "Cursed" Programming Language: github.com/ghuntley/cursedOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Capital One operates less like a traditional bank and more like a "technology company that happens to do banking." Ameesh Paleja, EVP of Enterprise Platforms, joins the show to explain how this philosophy empowers their 14,000 technologists to innovate at the speed of a startup despite operating in a highly regulated industry.Watch: 2026 Benchmarks InsightsFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest(s):Learn more: capitalone.com/techRead the blog: capitalone.com/tech/blog/Connect with Ameesh: LinkedIn | X (Twitter)OFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

As the year draws to a close, the Dev Interrupted team reflects on a transformative year in engineering spanning the rise of RAG and vector databases to the emergence of agentic workflows. For the first time, we’re taking the conversation out of the booth and into the IDE. Head over to the Dev Interrupted YouTube channel to watch the team vibe code custom holiday cards and close out the year with some chaotic creativity.Watch Part 2 on the Dev Interrupted YouTube channelFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

The common narrative suggests AI will make engineering leadership obsolete, but history - and the Industrial Revolution - suggests the opposite is true. Engineering executive Manoj Mohan joins the show live from ELC to argue that as code generation costs drop, the demand for high-level judgment and strategic oversight will only skyrocket. He breaks down why leaders must stop starting with models and start with customer pain points, utilizing his "3GF" framework to manage the risksLinearB: Measure the impact of GitHub Copilot and CursorFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest(s):Connect with Manoj: LinkedIn | SubstackOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

Is your engineering team wasting budget and sacrificing latency by pre-computing data that most users never see? Chalk co-founder Elliot Marx joins Andrew Zigler to explain why the future of AI relies on real-time pipelines rather than traditional storage. They dive into solving compute challenges for major fintechs, the value of incrementalism, Elliot’s thoughts on and why strong fundamental problem-solving skills still beat specific language expertise in the age of AI assistants.Join our AI Productivity roundtable: 2026 Benchmarks Insights*This episode was recorded live at the Engineering Leadership Conference.Follow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest(s):Elliot Marx: LinkedIn Chalk: Website | Twitter/X | CareersOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

After hitting a low point last year, developer job satisfaction is officially on the rise. Erin Yepis returns to the show to unpack the 2025 Stack Overflow Developer Survey, analyzing how autonomy and compensation are driving this recovery. We also cover the happiness gap between senior and junior engineers, the surprising drop in trust for AI tools, and why vibe coding is failing to catch on with professional engineers.LinearB: Measure the impact of GitHub Copilot and CursorFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest(s):Read the full report: 2025 Stack Overflow Developer SurveyStack Overflow Blog: Read Erin’s analysis and moreErin Yepis: Connect on LinkedInOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.

When you co-create Kubernetes, you earn the right to have strong opinions on the next platform shift. This week, Ben sits down with Craig McLuckie, Co-founder & CEO of Stacklok, who is advocating for a shift in leadership mindset. He argues we need to move from asking if we can use AI to demanding to know why we can’t. Listen to hear why he believes an "AI maximalist" philosophy is the only way to survive the next cycle.LinearB: Measure the impact of GitHub Copilot and CursorFollow the show:Subscribe to our Substack Follow us on LinkedInSubscribe to our YouTube ChannelLeave us a ReviewFollow the hosts:Follow AndrewFollow BenFollow DanFollow today's guest(s):Connect with Craig McLuckie: LinkedInCheck out Stacklok: Stacklok WebsiteOFFERS Start Free Trial: Get started with LinearB's AI productivity platform for free. Book a Demo: Learn how you can ship faster, improve DevEx, and lead with confidence in the AI era. LEARN ABOUT LINEARB AI Code Reviews: Automate reviews to catch bugs, security risks, and performance issues before they hit production. AI & Productivity Insights: Go beyond DORA with AI-powered recommendations and dashboards to measure and improve performance. AI-Powered Workflow Automations: Use AI-generated PR descriptions, smart routing, and other automations to reduce developer toil. MCP Server: Interact with your engineering data using natural language to build custom reports and get answers on the fly.