AI Coding
AI coding agents work like power tools
Coding agents shift a developer’s attention from writing every line towards architecture, testing and review.
Host and co-founder
Pete Winn
Co-host of Intelligence Snacks and co-founder of Other Stuff.
About
Pete brings a systems perspective to conversations about agents, software architecture and technological change.
Latest conversations
Episode 72
The Internet We Deserve
FIPS gives computers direct, secure addresses so their files and services can be reached without first moving them into the cloud. FIPS lets peers find a path to a computer or application, then carries IPv6 traffic across whatever underlying connection is available.
View episode ↗Episode 71The AI Industry is Wrong
Agents are useful for finding a path through unfamiliar work, but repeatable execution belongs in a bounded workflow. Reliable AI workflows keep known operations in ordinary code and call an agent only when flexible judgement is genuinely useful.
View episode ↗Episode 70The Malleable Computer
Signed device access could make locally hosted Autopilot WApps available through Wingman without turning every installation into a public internet service. Short, timestamped notes can bring more of a podcast into view while asking less of both the writer and the audience.
View episode ↗Latest ideas
Agents
Coding models have working personalities
Every coding model brings its own mix of literalness, initiative, caution and recurring habits to a coding session.
Software Systems
Domain experts can build software from operational knowledge
Coding agents let operators turn their knowledge of workflows, exceptions and commercial pressures into working software.