@emilkowalski I personally disagree because UI was never about the model used but mostly about personal taste. A bad designer with a great model will not produce something with the same quality and attention to detail as a good designer with a worse model
Introducing Claude Opus 5.5, the first model in our new Claude 5.5 family.
It performs at the level of Claude Fable 5.1 for most tasks, and costs 40% less to run than Opus 5.
@reymond______ different job. codex writes code, wh does the git chores around it e.g. giving you a ready worktree with .env copied, instantly, 0 tokens, handy for running agents side by side.Also uses different ai providers (local & free ones) and instead of writing queries u can click buttons