Yoonho Lee

There is a common negative sentiment I observe among ML researchers toward prompting, or more broadly, text optimization.

See the Meta-Harness project page.

A recent paper trains a model to predict which of two papers will receive more citations, and calls this learning scientific taste.

Paul Graham writes in “Maker’s Schedule, Manager’s Schedule”: There are two types of schedule, which I’ll call the manager’s schedule and the maker’s schedule.

Cross-posted from SAIL blog.