8 months of notion docs and 15+ hours of editing later, this is SquareDiff's first technical writeup on autonomous agent improvement.
We've ran obscene amounts of experiments, ran into countless bugs, and pushed hundreds of fixes. Here's everything we learned in building autonomous agent improvement through harness experimentation.
Asian parents raise their kids like how bad PMs manage their engineers: they just tell them what to do and get mad when they don’t do it exactly how they want