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

Are you at the top of your company's tokenmaxxing leaderboard yet? This week on the Friday Deploy, Andrew and Ben explore the controversial trend of "tokenmaxxing" sweeping through tech giants like Meta and Disney, as well as GitHub Copilot's shift to usage-based pricing that signals the end of the cheap AI era. The hosts also break down a terrifying incident where a rogue AI agent wiped out a production database and examine a new "vegan" language model trained exclusively on pre-1931 historical data. Finally, they react to a study revealing that 35% of all new websites are now AI-generated and close out the show with the drunk musings of a senior engineer. Read the guide: The APEX FrameworkFollow 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:An AI Agent Just Destroyed Our Production Data. It Confessed in Writing.Tokenmaxxing Is The Dumbest Metric In Tech Right NowIntroducing talkie: a 13B vintage language model from 1930Study Finds A Third of New Websites are AI-GeneratedFlipbook is an infinite visual browser generated entirely on demand in real time.Drunk Post: Things I’ve Learned as a Senior EngineerOFFERSStart 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 LINEARBAI 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.

What if deploying a new capability to an industrial robot arm was as seamless as pushing an update to a web app? This week, Andrew sits down with Brian Gerkey, CTO of Intrinsic and a titan of the open-source robotics community, to discuss how modern AI is finally giving robotics the "brains" to handle the unpredictable physical world. Brian breaks down how to move away from rigid, monolithic automation toward software-defined, modular robotics using tools like ROS (Robot Operating System) and digital twins. Finally, Brian invites developers of all backgrounds to test their skills in Intrinsic's new AI for Industry Challenge by using AI to solve one of the hardest problems in manufacturing: plugging in a tangled cable. Read the guide: The APEX FrameworkFollow 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:Brian’s Website: Learn more about Brian's work, research, and history in the open-source robotics community. Intrinsic: Explore the robotics software company led by Brian, which provides tools like Flowstate to build and deploy intelligent robotic solutions.AI for Industry Challenge: Get the toolkit and register to compete in Intrinsic's new challenge to solve complex dexterous manipulation and cable routing.ROS (Robot Operating System): The open-source middleware suite that has become the global standard for robotics software development.OFFERSStart 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 LINEARBAI 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 the era of cheap, unlimited AI tokens officially over? This week on the Friday Deploy, Andrew and Ben walk through the sudden wave of AI pricing chaos—from GitHub Copilot’s panic-paused signups to Anthropic's confusing pricing tests—and break down the terrifying Vercel security breach caused by a single over-permissioned AI tool. They also examine 12 game-changing architecture patterns exposed in the Claude Code leak to help you safely orchestrate your own agentic workflows. Finally, they discuss how to avoid the lethal trifecta of agentic security risks before mourning the tragic deletion of their Claude Code buddies.Read the guide: The APEX FrameworkFollow 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:Changes to GitHub Copilot Individual plansIs Claude Code going to cost $100/month? Probably not—it’s all very confusingAnthropic, OpenAI, Google, and Microsoft agree that the harness is the product. They disagree on the price.12 Agentic Harness Patterns from Claude CodeVercel April 2026 security incidentFragments: April 21Claude Managed Agents: get to production 10x fasterOFFERSStart 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 LINEARBAI 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.

Forget the massive GPU clusters. According to Tim Dettmers, research scientist at Ai2, you can build a state-of-the-art AI coding agent with what he calls a "hot plate and a frying pan." This week on Dev Interrupted, Andrew sits down with Tim to unpack how his resource-strapped team built the SERA model using a fraction of the compute power of major labs. They explore the tactical engineering behind synthesizing training data from private codebases without verification tests, proving that the open-source community is uniquely positioned to out-specialize frontier models. Finally, Tim shares his contrarian take on the future of token economics, explaining why the cost of AI might actually spike as compute efficiency hits a physical wall.OFFERSStart 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 LINEARBAI 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.

Have you or a loved one been afflicted by "brain fry" after managing too many autonomous agents? This week on the Friday Deploy, Andrew and Ben explore the cognitive toll of orchestrating AI swarms and share Kelly Vaughn’s expert strategies for avoiding burnout. The hosts also discuss Google's new campaign to punish websites that hijack the back button, the breakthrough of running Gemma 4 natively on mobile devices, and a new 8-step maturity model for building agentic data pipelines. Finally, they dive into a heated debate over whether Obsidian flat-files are a scalable memory solution for AI, comparing the methodology to Andrej Karpathy's new agent-compiled wiki system.Read the guide: The APEX FrameworkFollow 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:Introducing a new spam policy for "back button hijacking"Google Gemma 4 Runs Natively on iPhone With Full Offline AI InferenceWater Town: The Agent Swarm Data StackStop Calling It Memory: The Problem with Every "AI + Obsidian" TutorialThe Wiki That Writes ItselfBreaking out of the "brain fry" spiral of AIAfter Burnout by Kelly VaughnOFFERSStart 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 LINEARBAI 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.

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 "guardian agents," and what it takes to run a company with just 4 humans and 27 agents. Finally, they break down how to stop the chaotic game of telephone between engineers and business leaders by relying on "Deep-T" subject matter experts to evaluate what good AI output actually looks like.Read the guide: The APEX FrameworkFollow 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:Wayfound AI: Secure your autonomous enterprise and align your AI workforce with an independent agent supervision platform.Moltbook: Explore the viral social network built exclusively for AI agents, where you can observe Tatyana's OpenClaw agent, Aphasia, in action.Anthropic's Agent Autonomy Research: Read Anthropic's report on how people actually use agents and why post-deployment monitoring is an absolute necessity.OpenClaw: Explore the viral, open-source personal AI assistant framework.Follow Tatyana Mamut on LinkedInOFFERSStart 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 LINEARBAI 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 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 open-source models—including Gemma 4 and Holo3—and explain why modern AI benchmarks are proving that humans still have a cognitive edge. Finally, they wrap up by sharing how they deploy custom background agents to hack their way through expo floors at industry conferences.Read the guide: The APEX FrameworkFollow 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:Project GlasswingTool School: Benchmarking 101 (How To Read AI Model Report Cards)Four Open Models Just Proved You Can Own Frontier AI at Every ScaleJuliusBrussee/cavemanOFFERSStart 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 LINEARBAI 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.

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 Developer experience to ensure upstream code generation translates into actual business value. Tune in to learn how to break past the illusion of coding speed, prevent AI slop from clogging your review pipelines, and discover which pillar of the APEX framework your team needs to tackle first.Download the APEX FrameworkFollow 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:LinearB APEX Framework: Explore the full operating model, visual breakdowns, and the guide to operationalizing the metrics.Workflow Automation: Learn about LinearB's gitStream (policy-as-code for PR automation) and WorkerB (developer bot for minimizing idle time).OFFERSStart 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 LINEARBAI 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.

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, self-hosted models. Finally, they discuss the game-changing Pretext rendering library, the cyclical hype of "dead" tech trends, and how agent-wielding "vibe maintainers" are rewriting the rules of open-source software.Read the guide: The APEX FrameworkFollow 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:GitHub backs down, kills Copilot pull-request ads after backlashSoftware's Next Epoch: Our Investment in R.I.P. grepAnthropic accidentally leaked Claude Code's entire source. Here's what 512,000 lines revealShopify Cuts Inference Cost by 75x Using Qwen 3 for Merchant Data ExtractionPretext Does What CSS Can't — Measuring Text Before the DOM Even ExistsVibe MaintainerOFFERSStart 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 LINEARBAI 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.

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 explore the mechanics of Project Veto’s kernel-level security, the slow death of the traditional IDE, and how the rise of AI is transforming developers into full-stack, T-shaped product owners. Finally, Matt shares his vision for the future of the SDLC, detailing how organizations can safely balance strict compliance with the bleeding edge of autonomous software factories.Download the APEX FrameworkFollow 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:Learn more about Ona (formerly Gitpod) and read their latest blog announcements, including Veto.Connect with Matt on LinkedIn | X (Twitter)OFFERSStart 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 LINEARBAI 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.