author:daviddafrica

· 3 artifacts, sorted by favorites. · open in search — combine tags, sort, filter by date →

• @DavidDAfrica 2026-10-19 — Some new work, where we argue that functional welfare is a useful concept to study and understand AI safety and security ♥70
• @DavidDAfrica 2026-08-20 — Some new work with @natalia_lanzoni, @IrgolicR, and supervised with @merlinstein_, in the form of a blogpost on @aidiges ♥22
• @DavidDAfrica 2026-08-25 — We then combine these measures into a single score, and evaluate a wide variety of open models. Surprisingly, we find t ♥6