@garrytan: My friend @finbarr says: It's like code as memory. You work with your agent in a non deterministic way to figure out ho…

X AI KOLs Following News

Summary

Garry Tan discusses the concept of "code as memory" for AI agents, suggesting they generate executable scripts for new tasks and reuse them for efficiency.

My friend @finbarr says: It's like code as memory. You work with your agent in a non deterministic way to figure out how to execute a task. The first time it does a bunch of research and writes a script and then executes the script. Every future time it faces the same task it just executes the script immediately. The future is already here, it just might not be in your hands unless you decide to build it.
Original Article

Similar Articles

@garrytan: https://x.com/garrytan/status/2061454423034110372

X AI KOLs Following

Garry Tan argues that developers are over-engineering with excessive code when using AI agents; instead, they should trust the model and build minimal, instruction-based software, exemplified by his open-source project GStack.

@garrytan: https://x.com/garrytan/status/2054064931515855118

X AI KOLs Following

Garry Tan argues that AI coding agents like Claude Code and Codex have changed software engineering by making high test coverage affordable, creating a 'complexity ratchet' that ensures code quality improves over time without sacrificing speed.