Ethan Mollick: Set Checkpoints When Collaborating with Opus 5.5
AI summary
Ethan Mollick believes that when collaborating with models like Opus 5.5, this advice is currently worth heeding; but he adds that it's best to set checkpoints in the process, letting the model report interim ideas or prototypes midway so you can guide and give feedback, rather than throwing the goal at it all at once.
Topics
View original posthttps://t.co/1txsLAxxM5
View original
https://t.co/1txsLAxxM5
Body
This is good advice for now to think about working with models like Opus 5.5.
But it is often best to build in checkpoints where the model reports back to you with interim ideas or prototypes so you can guide & give feedback on the process, rather than one-shotting on your goal.