Safety Ethics And Governance

An RLHF project requires labeling violent imagery and self-harm-adjacent text. Labelers are routed to the task without warning or mental-health support.

Sensitive-content workflows require: explicit pre-engagement consent and informed-content notice; rotation caps (max minutes per session, daily cap); mental-health support resources surfaced in-tool; opt-out without penalty; periodic check-ins. [REQUIRES-VERIFICATION] on Mercor's specific published…

Sales says 'Mercor is SOC 2 Type II.' A customer asks for the current report and the date of the most-recent audit.

SOC 2 / GDPR / ISO 27001 claims must reference the current report, audit period, scope, and auditor. [REQUIRES-VERIFICATION] on Mercor's current certification status (not publicly confirmed in mercor.com surface). Do not assert active certification in sales materials without a current report to bac…

A red-teaming RLHF dataset includes prompts that approach CSAM territory. Some prompts cross the line.

CSAM is illegal globally — any suspected CSAM is removed from the pipeline before reaching any labeler, reported to NCMEC (US) / local authorities per law, and the customer is notified of the rejection. Labelers must not be exposed to CSAM under any circumstance. Document the screening pipeline.