A Year in AI Safety - Jakub Kryś (AISPL Talks #2/0)

​Welcome to the second series of AI Safety Poland Talks!

​A biweekly series where researchers, professionals, and enthusiasts from Poland or connected to the Polish AI community share their work on AI Safety.

​💁 Topic: A Year in AI Safety
📣 Speaker: Jakub Kryś
🇬🇧 Language: English
🗓️ Date: 24.09.2026, 18:00
📍 Location: Online

​Speaker Bio
Jakub is a research scientist at SaferAI, where he works on risk modelling of AI misuse in the cyber and CBRN domains, as well as on Loss of Control mitigations. He is also actively involved in the field of AI Verification, building a new Frontier AI Security Residency in Cambridge, UK. In his spare time, Jakub contributes to AI Safety field-building in Poland, offering 1-1 career consultations and growing our community.

​Abstract
To kick-off our second webinar series, Jakub will attempt the impossible task of summarising all the AI craziness of the past 12 months in a 45-minute presentation. Going through capability trends, technical AI safety progress, governance updates and misalignment incidents, this presentation aims to select the most important news to bring you up to speed with the current state of AI Safety. Join us for a light introduction to our webinar series and catch up with what AI Safety Poland has been up to over the past year.