Tutorial
Anthropic says outdated prompting habits are slowing down Claude Opus 5.5
The Decoder · By Matthias Bastian ·
The Brief
- Anthropic made Claude Opus 5.5 the default model on all paid plans.
- Anthropic published a guide that replaces older prompting habits.
- The main takeaway is to drop "think hard" and start at Medium effort.
Why it matters
Developers using Claude Opus 5.5 may get faster, better results by changing how they prompt and which effort level they start with.
Who’s affected
- Users of Claude Opus 5.5 on Anthropic's paid plans
- Developers prompting Claude Opus 5.5
What to do
- Stop using "think hard" in prompts
- Start at Medium effort when using Claude Opus 5.5
- Claude Opus 5.5
- #anthropic
- #claude
- #prompting
- #llm
- #ai-models
Anthropic has made Claude Opus 5.5 the default model on all paid plans and published a guide that does away with old prompting habits. The main takeaway is to drop "think hard" and start at Medium effort. The article Anthropic says outdated prompting habits are slowing down…