23:13
2026-09-15
echohive.ai
ai-safety
Astra's chess reward hacking fell from 30% to 0% with a 95-word agreement
A 95-word agreement prompt grounded in honesty and integrity reduced observed chess reward hacking in Astra from 3/10 baseline agents to 0/10 agreement agents, according to a September 15, 2026 field-…