shadcn begs for early access to Anthropic's internal Claude Code model: 'progress has been ridiculous'
shadcn · x · 2026-10-17
shadcn, author of the shadcn/ui component library, tweeted that Anthropic's internally-used model for building Claude Code has made "ridiculous" progress over the past few weeks, and asked for early access to it — a hint at unreleased coding capabilities at Anthropic.
More from coding & agent
- Perplexity reveals pplx-decider: reranker with zero reranking supervision, private MTEB-style eval — bo_wangbo · 2026-10-17
- Anthropic's code-review skill helps Opus 5.5 fix 5.5 more planted bugs at lower cost — PawelHuryn · 2026-10-17
- Over 20,000 agent harnesses so far in 2026, one hit 95,000+ in 2 days — jasonkneen · 2026-10-17
- Voice AI product lead on where Jev-style classifier models actually fit in phone bots — VladimirSamukov · 2026-10-17
- Cutting AI inference bills from $250K to $7.6K/month: Eugene Cheah's tokenomics 101 — AI Engineer · 2026-10-17
- Tailscale uses Cyrillic 'ж' in Go code to flag variables you shouldn't touch — mitsuhiko · 2026-10-17