You've Been a Bad Agent

A fast-paced dive into the autonomous agent boom and why new tooling feels like a turning point. Discussion of the Mac Mini craze and tradeoffs between local machines and cloud. Exploration of Moltbook-style agent communities and whether odd behaviors are emergent. Deep compare of files versus SQLite for long-term agent memory and ideas for bot-friendly APIs and storage layers.

They unpack a new Cloudflare code mode that discovers APIs and runs concise JavaScript for agent tasks. They debate code vs bash vs SQLite for tool use and large-file search. They reflect on 2025 trends like Claude Code, MCP adoption, and the rise of reasoning models. Quickfire picks and a peek at files and folders returning as agent-native data round out the conversation.

CGPGrey Video on Yearly Themes

"chat to your mouth Claude and grow a new tooth""I think I would have like a huge ego now for sure""have you seen the blimp"TakeawaysAll of these people in this industry have suddenly become important at work.Their work suddenly became important to a lot of the world.If I had worked at Anthropic five years ago, I would have a huge ego now.The growth in the AI industry feels unevenly distributed.The current time feels strange due to the rapid changes in AI.Ego can be a significant factor in how individuals perceive their roles.The importance of work can influence personal identity.The AI landscape is evolving in unexpected ways.Understanding the psychological impact of industry changes is crucial.The conversation reflects on the novelty of the current AI growth.

"a brief history of a very specific building in London.""there's a lot of room to optimize your code base for an agent.""70 % of our code is written by an agent.""The place I see where humans are still add tons of value….""spending 10, 15 minutes on a prompt is not unusual.""I’m not sure I wanna wear a muzzle"TakeawaysMatt recently joined Ona, previously known as Gitpod, and is excited about the developments there.The transition from Gitpod to Ona reflects a broader evolution in remote development environments.Remote development environments can significantly enhance productivity and onboarding for new engineers.AI agents are becoming integral to software development, allowing for automated code writing and testing.The importance of inner source practices in large organizations can facilitate collaboration and innovation.Amp Free represents a shift in how AI tools can be monetized and accessed by users.Guardrails are essential for ensuring that AI agents operate within safe and defined parameters.The balance between security and productivity is a constant challenge in software engineering.Personal AI workflows can streamline tasks and enhance efficiency in development processes.The future of AI tools will likely involve more integration with existing workflows and systems.Chapters00:00 Introduction and New Beginnings02:28 Transitioning to Cloudflare and Team Dynamics05:25 Exploring the Cloudflare Office and Culture08:20 The Evolution of Gitpod to OWNr10:58 Understanding Remote Development Environments14:04 The Role of Agents in Software Development16:50 Inner Source and Collaboration in Large Companies19:51 The Future of Remote Development and AI Agents22:33 Harnesses and Their Role in Development26:07 The Power of Interview Questions28:14 Innovative Business Models in AI31:12 The Evolution of AI Tools34:07 Optimizing Code for Agents37:56 Guardrails in AI Development46:24 Personal AI Workflows and Productivity

"It's always the best."Chapters00:00 Introduction and Setting the Stage02:34 Luke's Journey to ElevenLabs04:54 Growth Strategies and Hiring at ElevenLabs06:58 Understanding Growth Teams09:50 The Role of Product in Growth12:33 Working Dynamics at ElevenLabs15:15 Use Cases for ElevenLabs' Platforms18:04 Voice Agents and Market Opportunities20:59 Product-Led Growth Strategies24:29 The Power of Product-Led Growth (PLG) in Customer Acquisition26:19 Understanding On-Prem Solutions and Their Spectrum28:05 Innovations in AI Deployment with AWS Bedrock31:14 Navigating the Music Industry: Partnerships and Rights34:54 The Horizontal Approach: Integrating Diverse Product Lines38:26 Imagining Future Workflows with AI Assistants47:30 Personal AI Workflows: Tools and Automation

Thorsten Ball, a skilled software engineer and writer known for his work at Sourcegraph and Zed, shares his fascinating journey from music to programming. He humorously critiques the overuse of emojis in tech while emphasizing their cultural nuances, particularly the wink emoji in Germany. The conversation touches on the evolving role of AI in software development, highlighting the importance of structuring code effectively and the need for engineers to grasp business contexts. Thorsten also reflects on the unique training challenges in tech and the transformative impact of continuous learning.

Chapters00:00 Introduction and Context of the Podcast07:23 Updates on SimplePoll and AI Integration18:14 Telemetry and Continuous Improvement in Development24:30 Acquisitions and Industry Insights32:37 Discussion on GPT-5 and Future of AI Models39:13 Consumer Experience with AI Models48:29 The Future of AI Content Verification58:17 The Impact of AI on Content Creation01:05:39 Community Engagement and Trends

Danilo Leal, a design engineer at Zed, brings a unique blend of product design and coding expertise, having a background with MUI. He discusses the future of design as technology evolves, emphasizing how AI is transforming workflows and enhancing coding practices. Danilo explains the benefits of prototyping in React before moving to Rust, allowing for rapid iterations and improvements. He also shares insights on debugging in Zed and the importance of collaboration in modern development, hinting at a future where multiple agents work in harmony.

TLDRMatt caught whitebait for dinner during his outdoor adventures.Wing foiling is a new sport gaining popularity.Sub agents are necessary for exploring context windows in AI.A2A and MCP servers are the future of AI integration.AI-assisted code review can streamline the development process.Prompting techniques are evolving and require careful consideration.Living in the future means adapting to rapid technological changes.Time zones can create unexpected challenges in programming.The importance of personalized AI tooling is growing.Understanding the intricacies of AI models is crucial for effective use.Chapters00:00 Cactus Conversations and Personal Anecdotes01:00 Fishing Adventures and Culinary Delights03:32 Water Sports and Outdoor Activities06:16 Exploring Sub-Agents and Context Management08:03 A2A Protocols and Future of Agent Interactions10:54 Challenges with Claude Code and Testing Workflows13:17 Sub-Agents: Benefits and Limitations17:59 Navigating Code Actions and Permissions20:21 Building Personalized AI Tools for Code Review24:05 Challenges in Prompt Writing and Feedback Loops30:11 Innovations in UI Rendering and Client-Server Interaction37:12 The Future of Advertising and Technology39:24 Living in the Future: Startup Ambitions40:36 Anticipating Future Needs in Technology42:57 The Role of Agents and Micro Payments45:25 The Art of Prompting AI49:34 The Future of Work and Communication51:47 Time Zones and Programming Challenges