@danshipper: as usual claire and i are on the same page
Summary
Claire Vo announces the release of Opus 5, a model she dislikes using but which ranked highest in a blind test against Fable and GPT-5.6. Dan Shipper echoes agreement.
View Cached Full Text
Cached at: 07/25/26, 06:10 PM
as usual claire and i are on the same page
claire vo 🖤 (@clairevo): BIG NEWS: Opus 5 is here…and I hate working with it.
And yet in a blind taste test, I ranked it above every other model (even Fable and my beloved GPT-5.6)
What I cover in my day 0 review: 00:00 Why I have model fatigue 03:15 First impressions 06:12 Opus 5’s neurotic
Similar Articles
@danshipper: BREAKING: Claude Opus 5 is OUT NOW! And…it’s a hard model to love. We’ve spent the last week @every testing it across c…
An early vibe check on Claude Opus 5 finds it breaks backward compatibility with existing workflows but shows brilliance when starting from scratch, occupying an awkward middle ground between genius and generalist models.
@danshipper: This is wrong, it’s the same model But it does fall back to Opud 4.8 slightly more, so the benchmarks are measuring a m…
Dan Shipper argues that the Fable 5 model is not nerfed but falls back to Opus 4.8 more often, causing mixed benchmark results, contrary to claims of severe degradation.
@garrytan: Opus 5.5 with Openclaw is strangely smarter and better at completing tasks than with GPT-6 Astra Surprising
Opus 5.5 with Openclaw is described as surprisingly smarter and more effective at tasks compared to GPT-6 Astra.
@corbin_braun: wait... Opus 5.5 is better than Fable 5.1? is this true @grok
A tweet questions if Claude Opus 5.5 outperforms Fable 5.1, referencing Cursor's announcement that Opus 5.5 is now available as the top model on CursorBench with 40% lower costs.
@mattshumer_: I've been testing GPT-6 Sol for a bit now. It's solid, but I still prefer Astra/Fable 5.1 (and now, likely Opus 5.5) fo…
Matt Shumer tests GPT-6 Sol and shares his preference for Astra/Fable 5.1 and Opus 5.5 models, while referencing OpenAI's announcement of faster and more affordable GPT-6 Sol and Luna models.