1. Coding assistants based on o1 and Sonnet are pretty great at coding with <50k context, but degrade rapidly beyond that.
2. Coding agents do massively better when they have a test-driven reward signal.
3. If a problem can be framed in a way that a coding agent can solve, that speeds up development at least 10x from the base case of human + assistant.
4. From (1)-(3), if you can get all the necessary context into 50k tokens and measure progress via tests, you can speed up development by 10x.
5. Therefore all new development should be microservices written from scratch and interacting via cleanly defined APIs.
Sure enough, I see HN projects evolving in that direction.
Might be a boon for test-driven development. Could turn out that AI coding is the killer app for TDD. I had a similar thought about a year ago but had forgotten, appreciate the reminder
About 50 longer-form essays over the last ~5 years, mostly about venture capital, software, and developer productivity.
Some interesting Hacker News discussions on a few: Remote Software Developers Earn 22% More Than Non-Remote Developers (377 points) - https://news.ycombinator.com/item?id=22935476
Why We Will Never Have Enough Software Developers (366 points) - https://news.ycombinator.com/item?id=31724942