Repair Safety Drift with SafeTune
Use SafeTune and AuditKIT to audit and repair safety drift in a small Cohere Labs model, reporting before-and-after safety metrics.
Lexsi Labs, Cohere Labs, Hugging Face · on Lexsi
This hackathon has ended. Submissions closed on 2026-11-16 11:59 UTC.
Red-team, fine-tune, and audit open-weight language models in a fully online, 14-day AI safety and alignment build.
We checked the deadline, prize and entry rules against the organizer's page. The summary, ideas and FAQ were written by AI from those facts.
New events that match your topics, every Monday. Unsubscribe anytime.
Prizes listed: $30,000+ in prizes and credits combined. The cash part is not stated. First place is worth $3,662 in credits plus six months of Hugging Face Pro per teammate.
Use SafeTune and AuditKIT to audit and repair safety drift in a small Cohere Labs model, reporting before-and-after safety metrics.
Post-train a small Cohere Labs model with AgentTune for more accurate, efficient, reliable tool calls, then measure gains with AuditKIT.
Use CircuitKIT to find, evaluate, and intervene on safety-relevant circuits in a Cohere Labs model, reporting before-and-after metrics.
Browse more: AI Safety hackathons
Guides: For students · New to AI · Experienced builders