The real variable in whether your team needs formal evals is the distance between the people building the product and the people using it.At Anthropic, the people training models, building the harness, building the product, and using the product all sit inside one set of walls. Feedback circulates with almost no friction. That's why Claude Code can operate without a formalized eval process. Builder and user are the same person.Ankur Goyal's parents are both doctors. When he talks to them about t
52:06
The real variable in whether your team needs formal evals is the distance between the people building the product and the people using it.At Anthropic, the people training models, building the harness, building the product, and using the product all sit inside one set of walls. Feedback circulates with almost no friction. That's why Claude Code can operate without a formalized eval process. Builder and user are the same person.Ankur Goyal's parents are both doctors. When he talks to them about t
301.1K views3 months ago
x.comAakash Gupta
Synecdoche, New York
2:03:00
$
Synecdoche, New York
May 26, 2024
Google
See more
Static thumbnail place holder