Hands-on: Anthropic's Opus 5.5 one-shots dashboards and tables but keeps the 'Claude smell'
soleio · x · 2026-09-25
- A viral vibe check claims Opus 5.5 is hilariously good at in-distribution design, reliably one-shotting tables, dashboards and sidebars — more so than fable and astra.
- The model is noticeably faster, has higher verbal IQ, and tracks 2026-era SaaS visual trends closely, even preferring to draw its own icons instead of using icon packages.
- Drawback: outputs still carry a strong "claude-smell" — beige backgrounds with blue and orange highlights — though it can be prompted away.
More from coding & agent
- As models improve, writing good evals gets harder and more important — amankhan · 2026-11-12
- Omarchy 4.6 lets you share local AI models across your tailnet, says DHH — alexcovo_eth · 2026-11-12
- Coding harnesses hand shell access to inference providers — 4-step gateway mitigation — shensi · 2026-11-12
- Slack's David Hoang: agents beat people on coordination, proposes 'boundary agents' — davidhoang · 2026-11-12
- CS student mourns coding flow states he'll never experience in the AI era — chrissyykat · 2026-11-12
- AI Engineer Code Summit features its first all-female keynote lineup — altryne · 2026-11-12