Dev hands-on: new Claude model is chattier than Opus but far less than Sonnet 5
felixrieseberg · x · 2026-09-29
Developer Felix Rieseberg shared early impressions of the new Claude model: it's more talkative than Opus but far less yappy than Sonnet 5. He admits it's not perfect, but argues Sonnet was never better — a first-hand take on the new model's verbosity.
Related event: Dev Test: New Model's Verbosity Falls Between Opus and Sonnet(2 posts)→
More from Models
- Sonnet 4.5 turns to refusals and apologies right after producing a good text — repligate · 2026-09-29
- Astra 6 is smart but writes some absolutely terrible code — neil_conway · 2026-09-29
- Claude Sonnet 5.5 lands on Venice with anonymous access — juanbenet · 2026-09-29
- Sonnet 5.5 Lands in Conductor, and the Benchmark Chart Is Surprising — charlieholtz · 2026-09-29
- Opus 5.5 sets Bug Hunt Bench record with 800+ self-check turns — PawelHuryn · 2026-09-29
- Tip: don't use Sonnet 5.5 at max — it's dumber and far more expensive; high hits the best cost per task — airesearch12 · 2026-09-29