Self-promo
Whitepaper planned on gaps in harmful AI manipulation research and governance
A COLM 2026 attendee says they're also seeking AI safety research roles in threat modeling, strategy, evaluations and technical governance.
TLDR
On October 5, 2026, a COLM 2026 attendee said they were thinking about what's missing in harmful AI manipulation research and governance, with a whitepaper forthcoming. They also said they were looking for AI safety research roles, especially in threat modeling, strategy, evaluations and technical governance.
Combined views
810
1 Source, first seen ago
