Hacker News
points by alex_hirner 4 days ago | 0 comments
As ML practitioner it's quite obvious that the current advantage of Anthropic is sourced from the 30 or something days it collected essential code/prompt data during the Fable rollout.
[–] user43928 4 days ago
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