19:00 - 22:00
Schiller Street 25, 34117 Kassel
Our next meeting of the AI Safety Meetups takes place on 09.10.2025 Back in the Flipdot e.V. in the Schillerstrasse 25, 34117 instead of.
From 18:45 Are the doors open
19:00 c.t. The alignment problem (Vortrag von Max)
To 22:00 discussion (und Pizza)
Über Uns
Die rasante Entwicklung künstlicher Intelligenz schreitet – scheinbar unaufhaltsam – voran. With every progress towards Artificial General Intelligence (AGI) and possibly artificial superintelligence (But) the challenge grows, To reconcile these systems with our human values and goals-the so-called alignment problem. Despite the enormous scope, we have not yet solved this, While leading AI laboratories are continuously exploring more powerful models in the race for market shares. Experts have been warning for years, that this procedure can have catastrophic consequences. At our regular meetings (~ third Thursday of the month) We want to discuss current developments in the area of the first Kassel regulars' table for AI security, Discuss various approaches to the AI alignment and potentially think about it, How we, as individuals, can contribute to a safe AI future. We bring both a technical background, as well as mere interest in the topic, That from the high relevance and priority of AI security (also in contrast to other global problem areas) grow. Our meetings can be found in the Flipdot e.V. instead of. If you are interested or questions, you will reach us at Or via matrix in our digital sofa corner.