It was one prompt, claude verified pretty well too! No bugs so far
@bcherny
-
Choosing reasoning effort levels for Opus across models
By
–
For complex visual stuff with Opus xhigh/max, but 95% of the time I stick to medium. The best default is different for each model
-
Prompting Claude like a coworker, no scaffolding needed
By
–
I am surprised that people are surprised this is how I prompt Claude. Talk to Claude the way you would a coworker. There's no secret to prompting. There's no need to be overly scaffolded or prescriptive for most tasks — give Claude a goal, and it will figure it out. Back in
-
Claude reads transcript and primary sources
By
–
Claude decided to read the transcript and also a bunch of other primary sources. Full prompt above
-
Feedback sought on Claude Code Desktop AI tool
By
–
Curious if you’ve tried Claude Code Desktop recently. It’s quite good now, would love to hear what’s missing or could be improved
-
Customize Claude with prompts and share mods as plugins
By
–
Mods are absolutely insane. You can now customize Claude to work and look the way you want by just prompting it.
— Boris Cherny (@bcherny) 1 octobre 2026
Each person works differently, so there's no reason why everyone should have an identical Claude experience. Make Claude your own, and share mods as plugins so others… https://t.co/FxQ8ggZ0uKMods are absolutely insane. You can now customize Claude to work and look the way you want by just prompting it. Each person works differently, so there's no reason why everyone should have an identical Claude experience. Make Claude your own, and share mods as plugins so others
-
Ask Claude to update its commit attribution setting
By
–
Yep, just ask Claude to update its commit attribution setting
-
Daily use of Claude for various professional tasks
By
–
I mention Claude several times a day to write PRs, respond to user feedback, investigate incidents, perform data analysis, summarize information, etc. Use it as a search engine for your company. "What is the status