ARIA funds 8 teams with £22m to build formally verified LLM serving infrastructure
satnam6502 · x · 2026-09-24
ARIA is funding eight teams with £22m to test whether AI-enabled formal methods can make high-assurance cyber defence practical at unprecedented speed and scale, as AI-enabled cyber attacks accelerate.
Cornell's Nate Foster announced he will collaborate with afdicl and colleagues at Imperial College London and EPFL on building formally verified LLM serving infrastructure.
Related event: UK's ARIA Puts £22M Into AI-Enabled Formal Cyber Defense(3 posts)→
More from Safety
- Spinning up containers for 20-line agent tools is backwards: Safescript compiles provable, 50ms-deploy apps — uriwa · 2026-11-12
- Zvi dissects Anthropic's latest system card, disputing the autonomy threshold call — Don't Worry About the Vase (Zvi) · 2026-11-12
- AI Analysis of 42 Jensen Huang Podcasts Tracks Shift on China and Chip Controls — ShakeelHashim · 2026-11-12
- Small AI sites under 20 MW mostly skip the permitting fights battering big data centers — antavedissian · 2026-11-12
- Newsweek op-ed: US should fund hospitals and universities in federated AI learning — Saul_Loveman · 2026-11-12
- Ron Bodkin: automated research taste advances faster than expected, but the evidence is weak — ronbodkin · 2026-11-11