The Decoder· Matthias Bastian·· 1 d ago
Anthropic says outdated prompting habits are slowing down Claude Opus 5.5
Anthropic says outdated prompting habits are slowing down Claude Opus 5.5
AI summary
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.
Selection record
Threshold 76Media and individualsFirst 58Second 58
Not admittedSum of both 116 < twice the threshold 152
- Source tier
- Media and individuals; this tier's threshold is 76
- Pre-filter
- passed：Anthropic提示词与模型使用建议
A model scores each item twice, independently, against one written standard, out of 100. An item is admitted only when the two scores add up to twice the threshold. The threshold is set per source tier.
Source: The Decoder · the-decoder.com