RSS

David Gringras

Karma: 18

Medical doctor and law graduate. Frank Knox Fellow at Harvard (Health Policy), cross-registered at MIT. Research fellow with Arcadia Impact’s AI Governance Taskforce. Currently pivoting from medicine, law, and health policy into AI safety/​governance; spending a lot of that time trying to figure out what transfers (and what doesn’t).

I Used Safety Bench­marks to Test Agen­tic Scaf­fold­ing. The Bench­marks Were More Bro­ken Than the Scaf­folds.

David Gringras24 Feb 2026 21:36 UTC
10 points
0 comments7 min readLW link