Ethan Mollick suggests setting checkpoints when collaborating with models

Oct 30

1. 22:29

   36Kr · AI

   Claude Code team member on how to reduce over-prompting Claude

   Addy Osmani, a member of the Anthropic Claude Code team, wrote in a post that users generally over-prompt Claude, and suggested using a single prompt to clearly state the goal and acceptance criteria, then letting the model execute on its own, with reasoning effort starting from /effort medium. He mentioned that Claude Code once removed more than 80% of the system prompts for models such as Claude Opus 5 and Claude Fable 5, with no measurable decline in coding benchmark performance, and suggested users use /doctor prompt-audit to find prompts written for older models. The article also suggests first making a single session capable of completing tasks independently before considering parallel multi-session work, and focusing attention on verifying results.

   Expand summary
2. 02:37

   Ethan Mollick

   Ethan Mollick: Set Checkpoints When Collaborating with Opus 5.5

   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.

   Expand summary