Menu
Sign In Pricing Add Podcast

Decoder with Nilay Patel

Anthropic’s Mike Krieger wants to build AI products that are worth the hype

2604.668 - 2624.545 Mike Krieger

I would probably put it in three places. One is in the actual model training and fine-tuning, where part of what we do on the reinforcement learning side is saying we'd like to find a constitution for how we think Cloud should be in the world. And that gets baked into the model itself early, before you hit the system prompt, before people are interacting with it.

0
💬 0

Comments

There are no comments yet.

Log in to comment.