Intro
Highlights of the Week
Zen of AI Coding
https://nonstructured.com/zen-of-ai-coding/
The cost of changing your mind is lower than it has ever been. Architectural decisions that once felt permanent are now provisional. You chose React. Two months later, you regret it. Ask an agent to rewrite the project. Making imperfect decisions is no longer fatal. In fact, it can be productive. A flawed reference implementation provides better context than a pristine specification. Agents reason more effectively from concrete artifacts than from abstract intent. Rapid iteration is now the default mode.
Building for Trillions of Agents
https://x.com/levie/status/2030714592238956960/?rw_tt_thread=True
Just as designing for users meant putting yourself in their shoes when building software, the same is true when thinking about what agents will run into. For instance, Jared Friedman at YCombinator put everyone on notice: “Even the best developer tools mostly still don’t let you sign up for an account via API. This is a big miss in the claude code age because it means that claude can’t sign up on its own. Putting all your account management functions in your API should be tablestakes now." If an agent can’t easily sign up for your service and starting using it, you’re basically dead to agents.
We’re definitely going to see new forms of companies the next while but what they’ll be is another thing. This is and interesting idea where they could be ones that are more focused on agents and enabling agents than people. The agents are customers not people. For example Ramp released agent cards recently where you give it to the agent and it does what it wants within the limits of what you’ve set.
The Shape of the Thing
https://www.oneusefulthing.org/p/the-shape-of-the-thing
The process included two (quite radical) rules: “Code must not be written by humans” and “Code must not be reviewed by humans.” To power the factory, each human engineer is expected to spend amounts equivalent to their salary on AI tokens, at least $1,000 a day. The basic idea of the Factory is that it takes future product roadmaps, written by humans, and turns those into products. Coding agents use those roadmaps to build software while testing agents try out the software in a simulated customer environment (which the testing agents build as needed). The sets of agents provide feedback to each other, looping back-and-forth until the results satisfy the AI. Then humans review the finished product and the results are shipped to customers without anyone every touching, or even seeing, the underlying code.
AI Should Help Us Produce Better Code - Agentic Engineering Patterns - Simon Willison’s Weblog
https://simonwillison.net/guides/agentic-engineering-patterns/better-code/
I like to think about shipping better code in terms of technical debt. We take on technical debt as the result of trade-offs: doing things “the right way” would take too long, so we work within the time constraints we are under and cross our fingers that our project will survive long enough to pay down the debt later on.
AI can and should let us write better software. Technical debt doesn’t need to be a thing anymore. Small tasks that couldn’t get prioritised or
The Five Levels: From Spicy Autocomplete to the Software Factory
Level 3 is a Waymo with a safety driver. You’re not a senior developer anymore; that’s your AI’s job. You are… a manager. You are the human in the loop. Your coding agent is always running multiple tabs. You spend your days reviewing code. So much code. Your life is diffs. For many people, this feels like things got worse. And almost everyone tops out here. Level 4 is a robotaxi, and while it’s driving, you can do something else. You’re not a developer. You’re not a development manager either. You’ve now become that which you loathed: you’re a PM3. You write a spec. You argue with it about the spec. You craft skills (for Claude Code, because most folks at level 4 seem to find their way to Claude Code). You plan schedules. You review plans. Then you leave for 12 hours, and check to see if the tests pass.
This is what I’m having trouble with. I’m at probably level 2 which is just using Claude as a partner rather than delegating entire tasks to it and moving to a higher level. Understanding what the next levels look like is the first part of the problem for me