Skip to content
NewA calmer, faster ZeroHour

Anthropic says old prompting habits slow Claude Opus 5.5

Original title: Anthropic says outdated prompting habits are slowing down Claude Opus 5.5

The Decoderby Matthias Bastian ()3 min read1 · 1 read
AI summary · x-ai/grok-4.7Summaries by Vani AI

Anthropic says Medium effort matched predecessor Opus 5 on High, and phrases like "think hard" no longer help.

Anthropic says Claude Opus 5.5, now the default on Pro, Max, Ultra, and Team plans, reasons on its own and that leftover instructions from older models slow it down. The company advises dropping phrases such as "think hard," starting at Medium effort, stating the desired result in one message, and attaching diagrams as files. It also says teams that reserved Opus for hard work should reconsider that split with Sonnet.

Unconfirmed: Performance, cost, and quality claims come from Anthropic's own tests and are not independently verified here.

Key facts
  • Anthropic says responses without "think hard" started faster with no measurable quality drop.
  • In internal tests, Opus 5.5 on Medium matched Opus 5 on High.
  • Users who regularly set Sonnet to Extra High or Max pay about as much as Opus 5.5, Anthropic says.
  • Even at the lowest effort, image reading beat Opus 5 at its highest, the company says.
Explain this AI news with Vani AIWhat was announced, what is new and why it matters, in a new chat

From the original article

3 min read at the-decoder.com

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 Decoder

By Matthias Bastian · the-decoder.com

Read the full article at The Decoder

A short excerpt; the article and its images belong to the publisher. Summary, key facts and assessment above are AI-written from the article and can be wrong.