Why Tejal Patwardhan stopped underestimating the models - Episode 21

Hello, I'm Andrew Mayne, and welcome to the OpenAI podcast. How can we make these models useful for people in their real work?.

It goes beyond the title with direct discussion of like, model, think, including: On today's episode, we're talking to the research lead, Tejal Patwarden, about the need to build front-to-e valves as old benchmarks get saturated.

1. 01On today's episode, we're talking to the research lead, Tejal Patwarden, about the need to build front-to-e valves as old benchmarks get saturated
2. 02How can we make these models useful for people in their real work?
3. 03We don't know if the model is going to beat it