flâneur

Supervise Process, not Outcomes | Ought

ought.org · 3,108 words · saved by 1 readers

Machine learning systems are on a spectrum from process-based to outcome-based. This post explains why Ought is devoted to process-based systems.

Supervise Process, not Outcomes | Ought ought Table of Contents The spectrum Supervising outcomes Supervising process In between process and outcomes It’s better to supervise process than outcomes Differential capabilities: Supervising process helps with long-horizon tasks Alignment: Supervising process is safety by construction In the long run, differential capabilities and alignment converge Two attractors: The race between process- and outcome-based systems Outcome-based optimization is an attractor Process-based optimization could be an attractor, too The state of the race Conclusion Appen

saved by

related reading