Zach Lloyd(@zachlloydtweets):Our scorer agents noticed that our foreman was sometimes implementing changes directly, rather than passing them to our implementor (think of the foreman as our factory orchestrator). This isn't ideal because our implementor has special skills and model settings for coding. After this regression happened a bunch of times, our self-improvement agents noticed the pattern and suggested a fix to strengthen the prompt. We would have noticed this eventually, but having it happen automatically was magical.

Zach Lloyd

@zachlloydtweets

Trying to build impactful software. Founder @warpdotdev, former Principal eng @Google.

Joined July 2021

119 Following 20.5K Followers

Zach Lloyd@zachlloydtweets

2026.08.26 22:14

Our scorer agents noticed that our foreman was sometimes implementing changes directly, rather than passing them to our implementor (think of the foreman as our factory orchestrator). This isn't ideal because our implementor has special skills and model settings for coding. After this regression happened a bunch of times, our self-improvement agents noticed the pattern and suggested a fix to strengthen the prompt. We would have noticed this eventually, but having it happen automatically was magical.