The Coding Agency

Let's make software better

Make software work for you

The Coding Agency is on a mission to improve software outcomes through public literacy and better tools.

As software evolves, more people can bring ideas to life, and builders have new ways to work. It's equally clear that engineering fundamentals in the right places are more important than ever.

Meanwhile, we are bombarded with calls to adopt unstable solutions now or be "left behind." These are fear-based messages that confuse motion with progress.

AI as conceived by Silicon Valley is a political project, and the central feature of that project is to take agency away from people.

Karen Hao, author of Empire of AI

Big Tech has forgotten that software is for people. Agents should give you agency.

Latest

  • What Are Language Models Good For?

    Today we discuss the specific strengths of large language models and how they compare to classic symbolic AI. How can we explain what LLMS are good at? First, LLMs are good at language modeling (duh). That's the most accurate but least relatable explanatio...

    Show notes
  • Why Is AI Political?

    Today we examine what it really means for something to be "political", and consider the situation for engineers just trying to get things done when their technology becomes a controversy. Resources Why Linus is right and AI is wrong - Ray Myers, Is it eth...

    Show notes
  • Agentic Ransomware Has Arrived

    The industry is due for a crash course in cybersecurity as we look at the first documented AI-driven ransomware operation. Resources JADEPUFFER: Agentic ransomware for automated database extortion - SysDig report, OWASP Top 10 web application security ris...

    Show notes
  • Local Models

    Today we get our hands dirty running AI language models on our very own (and very hot) laptop! Exploring the tradeoffs, we see how this approach addresses common AI objections including privacy and resource usage. Local AI is a promising path, though still...

    Show notes
  • The Fable Ban and Doom Trolling

    High drama ensues as the US government forces Anthropic to take down it's new model Fable. How did we get here? In this episode, Ray and Liz unpack some of the context and put a critical eye on fear-based fundraising from top AI labs. Concepts AI Ethics, ...

    Show notes
  • My First App w/ Liz Martinez

    For our series premier, Liz Martinez joins host Ray Myers to design and build her first app using coding agents, with some bumps along the way! Concepts covered Product Requirements Document (PRD), Tech Stack, Domain Modeling, Blank Canvas Follow us onli...

    Show notes