Hacker News
points by user43928 4 days ago | 0 comments
How would you use such noisy data in a way that brings a large advantage over a pipeline of curated tasks?
[–] alex_hirner 4 days ago
You have to figure out messy real life tasks anyway (ambiguous reward signal, inconsistencies, variables outside the observation).

Having actual data just makes it more feasible.

[–] whimsicalism 4 days ago
very very easily