EPFL AI Center x UK AI Security Institute - mini-symposium — Evaluations, Impact, and the Science of AI Safety

Join us at the EPFL AI Center on Monday, Sep 29, for an on-site visit from the UK AI Safety Institute (AISI).

We’ll cover AISI’s current priorities, methods for sandboxing agentic evaluations, new evidence on the real-world impacts of AI advice, and the science of evals—closing with a poster session/networking apero.

! Registration is required to attend this event. Access is restricted to EPFL participants. !
Registration form (restricted to EPFL email addresses): https://forms.office.com/e/wPBhzPbzFP

Bring a poster—the apero session will highlight EPFL student work. When registering, select “Bring a poster” and add your title (limited slots).

Program

• 15:00 – 15:05 — Welcome, Prof. Antoine Bosselut, EPFL
   
• 15:05 – 15:20 — Opening & overview of AISI, Shannon Yang, UK AI Safety Institute (DSIT)
   
• 15:20 – 15:40 — Sandboxing agentic evaluations, Art O’Cathain, AISI
   
• 15:40 – 16:00 — Tracking real-world impacts of AI advice, Lennart Luettgau, A Large-Scale Longitudinal Study of Human User Behaviour & Wellbeing
   
• 16:00 – 16:15 — Short break
   
• 16:15 – 16:35 — The science of evaluations, Magda Dubois, AISI
   
• 16:35 – 17:00 — Talk by Eric Winsor

• Agentic evaluations & sandboxing frameworks
• Measuring real-world impacts of AI advice & wellbeing
• Science of evals: robust, transparent benchmarking
• Trustworthy AI practices: reproducibility, transparency, ethics