RESI launches to build scientific foundations for safe-by-design superintelligence
JessicaHullman · x · 2026-08-25
Shafi Goldwasser, Adam Kalai, and Vinod Vaikuntanathan have founded RESI (Institute for Responsible Superintelligence) in Cambridge. The goal is to build the scientific foundations needed to make superintelligence safe by design. Rather than relying on post-deployment testing and red-teaming, RESI aims to define safety properties in advance and achieve them through analyzable mechanisms, mirroring the historical shift in cryptography from ad-hoc patches to rigorous primitives.
More from Safety
- New paper uses revealed-preference methods to unpack why AI agents cooperate — brwilder · 2026-10-16
- Anthropic gives METR employee-level access, waives right to block its risk assessments — TechCrunch AI · 2026-10-16
- Berkeley scholars: concentrated chip supply chain makes a hardwired frontier AI pause feasible — wfithian · 2026-10-16
- Anthropic's GRAFT routes flagged gradients into a deletable adapter, cutting reward hacking to near zero — rohanpaul_ai · 2026-10-16
- Polymarket opens 50/50 market on more states banning Flock police cameras by end of 2026 — Polymarket · 2026-10-16
- Reproducing the Hugging Face security incident: a technical deep-dive, Part I — jessehu · 2026-10-16