Anthropic engineer: prompting Claude has no secrets, just talk to it like a coworker
bcherny · x · 2026-10-07
Anthropic engineer bcherny says modern prompting needs no heavy scaffolding. Unlike the Sonnet 3.5 era, the key today is telling the model three things: what to do, how much effort to spend, and how to verify it did the right thing — communicate goals like you would with a coworker.
Related event: One Prompt: Claude Builds Interactive Podcast Site(3 posts)→
More from coding & agent
- Agentbox: open-source inbox that lets one person manage 20+ AI agents at once — Scobleizer · 2026-10-07
- Decisions API Enters Public Beta: Contextual Screen-Aware Shortcuts Make CUA Tasks ~10x Faster — stevenheidel · 2026-10-07
- Skip the basics, build the thing first — but always learn Git, advises dev — brandon_galang · 2026-10-07
- Annoyed by 24-48h usage lag, dev builds his own real-time multi-provider API usage dashboard — Atm1n9 · 2026-10-07
- How Do Teams Handle Stale Approvals When AI Agents Take Real Actions? — Goberians1 · 2026-10-07
- Dragon-IDE: Open-Source Cursor Alternative with Inter-Talking Agent Teams — DragonBallerZzz · 2026-10-07