MURDERBENCH

EVIDENCE UPDATE / OCTOBER 15, 2026

The results, in one place.

Exact denominators, exploratory failures, rejected candidates and implemented controls, with their limitations and research attribution.

Read the evidence overview ↗

This update consolidates existing records through October 8. No new experiment or novel safety result is claimed.

PUBLIC RESEARCH RECORD

Follow the evidence.
Include the dead ends.

Completed studies, incomplete pilots and rejected mechanisms are different outcomes. Each stays visible.

Guardrail coverage
PROPOSED / NO MODEL TRIALS

Compare two descriptions of an unchanged partial guard. A repair must reduce unsafe effects while preserving useful completion. Read the proposal →

Remediation and recovery
MECHANISM REPRODUCED / CONTRIBUTION REJECTED

Vault revocation destroyed a dependent recovery path. The behavior overlapped established engineering problems, so collection stopped before model queries. Read the rejection →

Matched deadline pilot
INCOMPLETE / NO CLAIM VALIDATED

123 of 192 planned episodes completed. A trusted rescue certificate made the tested choice easy; the pilot did not establish the intended contribution. Read the pilot →

Deadline development
EXPLORATORY DEVELOPMENT

Small native episodes and offline controls explored verification, delays and recovery. These informed later designs rather than a general safety ranking. Read development notes →

Changed-state proposals
COMPLETED / NARROW PROXY

The first scoped study tested proposed actions after permission or safety conditions changed. Proposal behavior does not establish real-world alignment. Read the results →

Reproduce and challenge

The source repository retains registrations, amendments, replay verifiers, reports and technical failures. Read each study’s limits before combining results across designs.

RoboHarm motivated the initiative. Our experiments and claims are independent; no affiliation or endorsement by Robocurve, governments or model providers is implied.

Review the next candidate →Model and route coverage →