Skip to content

Anthropic publishes prompt guidance for Claude Opus 5.5

What happened

AI digest

On 15 November 2026, Anthropic issued guidance on how to prompt Claude Opus 5.5. According to The Decoder, Anthropic said some prompting habits carried over from older models slow Claude Opus 5.5 down, and recommends first removing phrasing such as "think hard", because the model reasons on its own and adjusts reasoning depth according to the task and the selected effort level. The current state is that Anthropic has publicly urged users to adjust their old prompting habits.

Written by AI from the reports · updated 1 d ago

Timeline

Follow the reports to see the event from each side.

Nov 15
  1. The Decoder
    Anthropic says outdated prompting habits are slowing down Claude Opus 5.5

    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.

Heat of this event

Current heat 4·Peak in the comparable range 9(Nov 15 05:00)·Change over 24 hours in the comparable range -49%

02.557.510Nov 1505:00Nov 1514:00Nov 1523:00Nov 1608:00

The trend compares only the same accounts observed without a break, so its range can be narrower than the current heat count. Move the pointer or tap the chart to see each hour; with a keyboard, use the left and right arrow keys.