Hiring a researcher/co-founder to study what character traits make AI agents safe

sebkrier · x · 2026-09-12

Cecilia Tilli is hiring a researcher / potential co-founder to build a team studying which propensities and character traits make AI agents safe in complex, multi-agent deployments. The effort is backed by coeffgiving, coopai and RethinkPriors; recommendations for candidates are welcome.

Original post →

More from Safety

Safety channel →