Lie, Is There a Recurring Theme for Machine Learning?

Onder cubenetis: It's usually just making sure that we are not setting a very low cap on how a pilot can scale. So even a like, small percentage of traffic, it's relatively easy for us to translate those settings to a model serving larger traffic. And once you have it kind of figured out there, um, there's not a ton you can do to make it better.

Transcript

Play full episode

Remember Everything You Learn from Podcasts

Save insights instantly, chat with episodes, and build lasting knowledge - all powered by AI.