The Creator of Claude Code on The Hottest Piece of Software in the World
- Source
- omny.fm
- Date
Context
Claude Code creator Boris Cherny argues that adopting agents requires changing how teams work together. In his Odd Lots interview, he describes an internal discussion at Anthropic about confusing interface icons. Claude gathered usage data and produced alternative designs, then a human designer joined the conversation.
His example places the inside a shared decision process, connecting a reported problem with evidence and possible changes. The hosts question how this would affect established job responsibilities. Cherny's answer is to equip the specialist with agents, making workflow redesign part of adoption. This is his account of working practice, rather than a measured productivity comparison.
- Cherny's case for why a safety lab built a coding tool: a model has no body, so the way it acts on the world is by writing code. Getting good at code is therefore inseparable from making the model safe to act.
- and interpretability inspect a model in the lab, but Anthropic's position is that you only learn whether it is safe by shipping it and watching people do real work with it. The product doubles as a safety instrument.
- Claude 3.5 was the break point: models went from finishing a line after a few keystrokes to writing a whole file or feature. That capability jump, not a product roadmap, is what made an agentic coding tool worth building.
- AI agent — An AI system that doesn't just answer once but works toward a goal in a loop — taking actions, reading the results, and deciding what to do next.
- agent harness — The scaffolding around a model that turns it into a working agent — the loop, the tools it can call, and the rules for when to stop.
- eval — A repeatable test for AI quality — a set of tasks plus scoring — used the way software teams use test suites, because model output is too variable to judge by eyeballing.
“Our computer language is going to be irrelevant in the future.”
“Everyone moves up to the higher order, more abstract thinking.”
“We're getting better at code, we're getting better at writing.”
Checking sign-in…
Loading comments…