You signed in with another tab or window. Reload to refresh your session.You signed out in another tab or window. Reload to refresh your session.You switched accounts on another tab or window. Reload to refresh your session.Dismiss alert
Two tracks are ready to start. We can only sequence one first. Weigh in.
Track A, VS Code extension (visibility). A headless tmux engine plus an xterm.js webview, so non-tmux users get the live agent panes inside a familiar editor. Lowers the floor for researchers who don't live in the terminal. ~2-4 weeks.
Track B, --low-token cost work (reach). Currently ~30% measured savings, structural ceiling. Push toward 50-60% via Haiku routing (shipped, pending second bench), then 70-80% via SDK refactor (prompt caching, Batch API, Files API). Multi-week, lands in v1.1.
If you're using ZO or planning to, which would unblock you sooner? Reply with A or B and a sentence on why, or leave a longer note.
reacted with thumbs up emoji reacted with thumbs down emoji reacted with laugh emoji reacted with hooray emoji reacted with confused emoji reacted with heart emoji reacted with rocket emoji reacted with eyes emoji
Uh oh!
There was an error while loading. Please reload this page.
-
Two tracks are ready to start. We can only sequence one first. Weigh in.
Track A, VS Code extension (visibility). A headless tmux engine plus an xterm.js webview, so non-tmux users get the live agent panes inside a familiar editor. Lowers the floor for researchers who don't live in the terminal. ~2-4 weeks.
Track B,
--low-tokencost work (reach). Currently ~30% measured savings, structural ceiling. Push toward 50-60% via Haiku routing (shipped, pending second bench), then 70-80% via SDK refactor (prompt caching, Batch API, Files API). Multi-week, lands in v1.1.If you're using ZO or planning to, which would unblock you sooner? Reply with A or B and a sentence on why, or leave a longer note.
Beta Was this translation helpful? Give feedback.
All reactions