Today I used Opus on high effort to do deep code spelunking to figure out how something worked across repos, develop an agenda for a meeting from it, then used Sonnet on medium effort to make sure the agenda was legible enough to me to present. It's backwards of how most people use the different models, using a higher-level model to check the lower one's work. I needed it because my level of understanding of the material is lower-fidelity than what Opus produced (correct, deeply researched, but opaquely presented)
It’s a great workflow. I think most of us are constantly figuring out which models work for which tasks. It’s important to keep working with the models to see what makes sense.
Today I used Opus on high effort to do deep code spelunking to figure out how something worked across repos, develop an agenda for a meeting from it, then used Sonnet on medium effort to make sure the agenda was legible enough to me to present. It's backwards of how most people use the different models, using a higher-level model to check the lower one's work. I needed it because my level of understanding of the material is lower-fidelity than what Opus produced (correct, deeply researched, but opaquely presented)
It’s a great workflow. I think most of us are constantly figuring out which models work for which tasks. It’s important to keep working with the models to see what makes sense.