Insights
Notes from the work: AI training, evaluation, and building agents that do real knowledge work.
Teaching machines to do real work: Part 2 of 4
How to design training exercises for AI agents
A spreadsheet of a few thousand training exercises turned out to be a few hundred scenarios sliced ten ways. Why row counts lie, why down-weighting cannot fix root imbalance, and how transplants add coverage without new task designs.
8 minutes
Teaching machines to do real work: Part 1 of 4
Reward hacking explained: how one bad grader teaches AI a thousand bad lessons
After pre-training, a model learns from a loop with three parts: (a) exercises define the situations it sees, (b) graders define what counts as better and (c) human experts are the quality check on whether the graders' idea of better matches a professional output.
6 minutes