Why CEREBRO kept it

Thinking-pattern change in Opus, anecdotal, unverified

Community take

Many users say Opus 5.5 reasoning degraded after Nov 3 and suspect a pre-release nerf, but the most useful correction is that only the thinking summarizer changed, not the model or its performance.

Backlinks

Appeared in 1 briefing

• 2026-11-09

Related

Shares tags: ai/llm-mechanics · cerebro/signal

• When Anthropic release a new model it's always worth taking a look at their updated prompting guide - here's an entertaining tip to make Fable 5.2 less likely to be cautious in how it improves existinx · 2026-11-10
• Really interesting though: when you switch to 'code only' mode (only uses code benches), the gap gets way smaller Also worth noting that xhigh and max score WORSE on the code benches compared to highx · 2026-11-10
• All my math here was done by analyzing over 1.1 million real requests to the Anthropic APIs using my Ultra $200 sub. I will continue to share updates as I have them :) https://t.co/7ozo1g12v4x · 2026-11-10
• The $200 Claude Ultra plan gets you $15,000 of Opus 5.5 in a month, but only around $3,000 of Fable 5.5. Even ignoring that Fable is restricted to 50% of your weekly limit, it burns faster per $ thanx · 2026-11-10
• As an Agentic AI Engineer in 2026. Please learn: 1. Context engineering & memory: what enters the context window, what gets summarised, what gets retrieved later. Otherwise the agent re-reads the sax · 2026-11-10
• Amazon saves millions by replacing Sonnet 4.6 with Strands Deciderhackernews · 2026-11-10

Also from twitter.com

Only signal from twitter.com so far.