Technical AI Safety
Evaluations of dangerous capabilities, interpretability, robustness, monitoring and control — the engineering side of keeping systems safe.
Save the date · Warsaw 2026
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
Why now
AI safety is one of the most urgent challenges of our time. Adoption across companies and institutions is accelerating. Only through a shared effort—across technical and non-technical backgrounds alike—can we mitigate the growing risks.
Join Warsaw AI Safety Day to meet people who care about making a difference, and take your first step—or your next one.
More room than slides
Around 250 researchers, builders, students and organisations working on, or moving into, AI safety. The first event of its kind in Poland.
There are talks from people doing serious technical and governance work—and real time between them for conversations, introductions and an organisation fair.
Most attendees get more out of the room than out of the slides.
Programme
Two parallel tracks, brought together by shared keynotes, lunch and the film premiere. Session titles and speakers are being confirmed now.
Opening keynote
Speaker to be announcedParallel tracks · technical & governance
Session titles to be announcedFilm premiere
Speaker to be announcedAfternoon keynote
Speaker to be announcedParallel tracks · technical & governance
Session titles to be announcedEvaluations of dangerous capabilities, interpretability, robustness, monitoring and control — the engineering side of keeping systems safe.
Institutions and incentives for frontier AI, evidence that travels from research into policy, international cooperation and capacity building in Poland.
The 1:1 layer
Inspired by the meeting culture at EAG events, protected gaps in the programme turn introductions into focused conversations.
Not random networking. A lightweight way to find collaborators, mentors, peers—or your next role.
A Polish first
The afternoon opens with the premiere of the first Polish-language popular-science film about AI safety—with English subtitles.
Made possible by a Rapid Grant from BlueDot Impact.
Voices in the room
The programme will bring together people doing consequential work across technical safety and governance.
Technical AI safety
AI governance
Alignment research
Responsible AI in industry
Who it is 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
One ticket, the whole day
59 PLNEarly bird until 20 September 202699 PLN afterwards
If the fee would be a barrier, email us for a complimentary ticket.
Included
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 placeBuilt together
Organising & strategic
Good to know
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.
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.
Admission to the full programme, a vegan catered lunch, and coffee service throughout the day.
The conference is held in English, start to finish. The Polish-language film premiere includes English subtitles.
24 October 2026 · Warsaw
We found it. It asked for good governance.