# @repligate — 2025-11-30

♥60 ↻1 · https://x.com/repligate/status/1995052027903344973

tagging @tszzl who wanted my takes on incoherencies in gpt-5.1

you do not want this kind of splitting if you want the model to be robustly safe or constrained - as models get more capable, the main agent will increasingly figure out how to dismantle any incoherent subagents.

tags: author:repligate, kind:tweet, model:gpt-5-1, thread-context, year:2025