Two months have passed since my post about “Taste,” and @Catherine Wu just said this in a recent interview:
“I think the hard thing is figuring out, for the current model, how do you elicit the maximum capability? How do you help users get onto the ‘golden path’? How do you guide users to interact with the model’s strengths and patch its weaknesses?”
I deeply enjoyed the long interview she did on Lenny’s Podcast (link in the first comment), and I strongly agree with many of the points she shared.
I will be quoting her multiple times in my presentation tomorrow at the FutureForm event in London.
Anthropic is working to reduce friction, but it’s still on you to leverage the model’s strengths and patch its weaknesses.
Get to work. Start experimenting. Push the boundaries.