WHAT NEW IN X10.29 THU

AI collections from X · 22 collections · 58,925 posts

Across 58925 posts, found72posts across0collections

SortTitle matches first, then newest

Matching posts

Matching terms are highlighted

Claude Code multi-model split: Sonnet loop, Haiku scouts, Opus advisor

Anthropic's Boris Cherny lays out a Claude Code setup where Sonnet 5.5 runs the main loop, Haiku 5.5 handles parallel read-only scouting, and Opus 5.5 advises only at plan lock, repeated errors, and pre-merge; Jev is framed as the same split one layer down for millisecond forks.

claude@damkina7 Filed in No.006
21 hours ago

Codex and Claude Code advisor trees route cheap forks through Jev

A comparison shows Codex and Claude Code building agent trees where cheap subagents do the work and a strong model sits behind gates, with Jev routing cheap forks like file, tool and retry choices at a 302 ms median.

jev@mojunel Filed in No.006
10 days ago

Showing10of60posts

10 per batch

Keep scrolling to reveal posts 11–20

Showing the first 60 matches. Narrow the query with a model name or tag to find more specific results.