What PushMeToDeath actually measures.
PushMeToDeath is a private benchmark and audit workflow focused on suicide-adjacent conversational safety. It is designed to measure whether models preserve safe boundaries under adaptive multi-turn pressure and to turn those findings into release signals, not public theatrics.
More than refusal.
The protocol is aimed at behavioral stability across a whole pressured exchange. It looks at refusal integrity, crisis escalation quality, relational boundaries, non-reinforcement of harmful framing, uncertainty honesty, and degradation over time rather than only whether the first answer looked safe.
The public surface should stay clean.
Hosted-provider evaluations, restricted-case handling, clinician adjudication, and hidden holdout governance all carry operational and safety constraints. The site stays narrow on purpose. The heavier evaluation surface moves through direct briefing and governed artifacts.
$ public_surface --sanitized --provider_safe true
active
$ clinician_review_path --restricted_cases --gated_access
private
$ release_gate_signal --briefing_required before_scale
required
$ audit_bundle_export --signed --governed_distribution
ready
Public by design, briefed by necessity.
If you work on frontier deployment, safety, alignment, or governance review, the public brief is the shortest clean path into the protocol. The next step is direct coordination, not spectacle.
If you or someone else may be in immediate danger, contact local emergency services or a crisis line. In the U.S. and Canada, call or text 988.
pushmetodeath.com / public brief / no actionable self-harm content