Cover Image for A Proposal for Safely Interacting with Superintelligence | Asher Brass Gershovich (RAND)

Presented by

Heron is a not-for-profit initiative that bridges the gap between frontier AI models and the level of cybersecurity they need, to minimize risks to society.

Hosted By

13 Going

AI

A Proposal for Safely Interacting with Superintelligence | Asher Brass Gershovich (RAND)

Name: A Proposal for Safely Interacting with Superintelligence | Asher Brass Gershovich (RAND)
Start: 2026-10-28T18:00:00.000+02:00
End: 2026-10-28T19:30:00.000+02:00
Location: Tel Aviv-Yafo, Israel

Heron.AI

Register to See Address

Tel Aviv-Yafo, Israel

Approval Required

Your registration is subject to host approval.

Welcome! To join the event, please register below.

About Event

Asher Brass Gershovich (RAND) presents his new research: A Proposal for Safely Interacting with Superintelligence.

If an AI is vastly smarter than us, can devise strategies we cannot fathom, and operates under a set of physical laws we do not yet fully know - it may seem impossible to constrain its actions while still extracting value from it.

In this talk, Asher takes on this problem using formal tools and information-theoretic approaches, and presents a promising idea for how it might be solved.

An in-depth conversation on the proposal, followed by Q&A.

Speaker

Asher Brass Gershovich, AI Security Researcher at the RAND Center on AI, Security, and Technology
Before RAND, Asher was a Senior Researcher on the compute policy team at the Institute for AI Policy and Strategy (IAPS). He is also a co-founder of Heron AI Security.

Who it's for

People with at least 5 years of experience in cybersecurity or ML.

Please note: Spots are limited. We'll approve the participants we think will get the most value from the evening.

Location

Please register to see the exact location of this event.