
Evaluating models without test data (Practical AI #194)
Changelog Master Feed
Is Burt a Good Advance?
Daniel Treisman: I was thinking about, like you mentioned, you mentioned Burt earlier. You can analyze that model and see maybe where the next biggest sort of offending area is and kind of address that. But at some point you have to ship your model, right? So maybe there's this process of using the tool to find sort of these like worse defending parts of your model,. And maybe like at a certain point you get to a point of diminishing returns or something like that...Treisman: This is a coarse grain tool. It's not meant to go in and study epoch by epoch and try to fine tune exactly what's going on.
00:00
Transcript
Play full episode
Remember Everything You Learn from Podcasts
Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.