Dev Slams Claude Desktop UX as Far Behind Codex, But Admits Its Models Excel at Design
alex_barashkov · x · 2026-10-03
Developer alexbarashkov publicly urged Anthropic to fix Claude's desktop app, arguing its UX/design quality bar is far below OpenAI's Codex desktop app and Cursor, despite Claude models still being better at motion and design tasks — which forces him to keep using it for some work.
Other developers chimed in, suggesting Claude desktop instead add compatibility with arbitrary endpoints and open models, as Codex does.
More from coding & agent
- Dev ports Meta's open-sourced Muse gadget to ESP32 devices, gets it running with Claude — alexandr_wang · 2026-10-04
- Engineer builds HDL benchmark in one day with Claude, originally estimated at 59 days — IgorCarron · 2026-10-04
- Latent communication papers: KV-cache integrity vs malicious agents and state-delta hybrid channels — burny_tech · 2026-10-04
- Codex beats Claude Code at computer use and brevity, says AI researcher — Yuchenj_UW · 2026-10-04
- Compiler-backed agent Benzi hits 78.2% SWE-bench Verified at under 10 cents per fix — DonkeyTheKing · 2026-10-04
- pstack 0.15.9 ships /correct skill that fixes agents by changing the environment — RachelVT42 · 2026-10-04