Registration open

Warsaw AI
Safety Day

One day for the people shaping safer artificial intelligence—across research, policy and practice.

24 October 2026Faculty of Psychology, University of Warsaw · Stefana Banacha 2D, Warsaw

Isometric illustration of Warsaw's skyline, including the Palace of Culture and Science and the Old Town
Saturday, 24 October 202610:00–18:00 · Registration from 09:00Faculty of Psychology, University of WarsawHeld in English

Speakers

Rishub Jain

Rishub Jain

CEO, Research Engineer

Sampura Research | Ex-DeepMind

Chloé Touzet

Chloé Touzet

Policy Lead

SaferAI

Risto Uuk

Risto Uuk

Head of European Policy and Research

Future of Life Institute

Karolina Korgul

Karolina Korgul

Doctoral Researcher

Google DeepMind | Oxford Internet Institute

David Quarel

David Quarel

Head of Teaching

ARENA

Christopher Stamper

Christopher Stamper

Biosecurity Researcher

Karolinska Institutet

Jakub Kryś

Jakub Kryś

Research Scientist

SaferAI, ERA

David Williams King

David Williams King

AI Safety Research Manager

ERA Cambridge

Jan Betley

Jan Betley

Researcher

Truthful AI

Anna Sztyber-Betley

Anna Sztyber-Betley

Assistant Professor

Warsaw University of Technology | Truthful AI

Justin Olive

Justin Olive

CEO

Generality Labs

Michał Kubiak

Michał Kubiak

AI Policy Expert

ORCG | AI Safety Poland

Chris Szulc

Chris Szulc

Managing Director

EA Poland

Jakub K. Nowak

Jakub K. Nowak

Executive Director

AI Safety Poland

Maciej Chrabąszcz

Maciej Chrabąszcz

AI Safety Researcher

NASK

Jan Broniowski

Jan Broniowski

LLM Consultant | AI Security Expert

Photo coming soon

Włodzisław Duch

Nicolaus Copernicus University in Toruń

Szymon Łukasik

Szymon Łukasik

Director of AI Safety Research Center

NASK

Psyho

Psyho

Who is it for

Curious about AI safety or governance and looking for a way in

Already in the field and seeking collaborators, mentors or a next role

Recruiting, researching or looking for institutional partners

Based in Poland or the wider region and committed to reducing advanced AI risks

Programme

Agenda

Two parallel tracks, brought together by shared keynotes, lunch and the film premiere.

View the full agenda
Doors open09:00

Coffee & registration before the programme begins at 10:00.

  1. 11:10

    Everyone together

    Shared programme from 10:00 to 11:10

    1. Opening & welcome

    2. Sampura Research: Hill-climbing Alignment using Humans

      Rishub Jain
    3. Coffee break

  2. 12:40

    Choose one track

    Parallel sessions

    11:1012:40
    Track 01

    Technical AI Safety

    1. Frontier LLMs RL training and its failure

      David Quarel
    2. Value Leakage: An LLM's Answers Are Silently Shaped by Its Own Values

      Jan Betley · Anna Sztyber-Betley
    3. Follow the Data: Understanding the AI Systems Attack Surface

      Jan Broniowski
    Track 02

    AI Governance

    1. From Rule-Takers to Rule-Shapers: AI Governance from the perspective of Middle Powers

      Michał Kubiak
  3. 15:05

    Everyone together

    Shared programme from 12:40 to 15:05

    1. Lunch & networking

    2. AI safety film premiere

    3. Enforcement Has Begun: the EU AI Act and Systemic Risks

      Risto Uuk
    4. Short break

  4. 16:35

    Choose one track

    Parallel sessions

    15:0516:35
    Track 01

    Technical AI Safety

    1. You could probably make a better alignment eval if you tried

      Justin Olive
    2. Biosecurity in the Age of AI

      Christopher Stamper
    3. Short introduction to Robotics Safety

      Karolina Korgul
    Track 02

    AI Governance

    1. Are existential risks a real problem right now?

      Jakub K. Nowak · Chris Szulc
    2. Introduction to AI Verification

      Jakub Kryś
  5. 17:00

    Everyone together

    Shared programme from 16:35 to 17:00

    1. Coffee break

  6. 18:00

    Choose one track

    Parallel sessions

    17:0018:00
    Track 01

    Technical AI Safety

    1. AI Monitoring Must Shift Beyond the Chain-of-Thought

      Maciej Chrabąszcz
    Track 02

    AI Governance

    1. Mniej oczywiste ryzyka rozwoju AI

      Psyho · Włodzisław Duch · Szymon Łukasik

The 1:1 layer

Make the meeting you came for.

Inspired by the meeting culture at EAG events, protected gaps in the programme turn introductions into focused conversations.

  1. 01Create a profile around what you work on and what you need.
  2. 02Discover relevant attendees in Swapcard.
  3. 03Send a meeting request with a short reason.
  4. 04Meet in a dedicated slot during the day.
15:30
Your next collaborator20 min · Meeting point C

A lightweight way to find collaborators, mentors, peers—or your next role.

Powered bySwapcard

AI safety, on the big screen.

The first Polish-language popular-science video explaining what AI safety is—with English subtitles.

Produced by
Piotr Kędziora
Runtime
20–25 minutes
Subtitles
English

Made possible by a Rapid Grant from BlueDot Impact.

One ticket, the whole day

59 PLN

Early bird until 20 September 202699 PLN afterwards

If the fee would be a barrier, email us for a complimentary ticket.

Included

  • Vegan lunch
  • Coffee service all day
  • Swapcard 1:1 meetings

Registration always has to be confirmed—signing up does not guarantee a place. Your answers in the form decide whether you are admitted.

Reserve your place

Good to know

FAQ

How much is a ticket?

Early bird tickets are 59 PLN until 20 September 2026. After that, tickets are 99 PLN. Every ticket includes the full programme, a vegan lunch and coffee all day.

Does registering guarantee a place?

No. Registration always has to be confirmed by our team—signing up does not guarantee a spot. Your answers in the form decide whether you are admitted, and we will email you once your place is confirmed.

What does the ticket include?

Admission to the full programme, a vegan catered lunch, and coffee service throughout the day.

What language is the event in?

The conference is held in English, start to finish. The Polish-language film premiere includes English subtitles.

24 October 2026 · Warsaw

Your next conversation could change your direction.

AGI?
Playful AGI illustrationWe found it. It asked for good governance.