Weekly Meetups
📍 Location
Maria-von-Linden-Str. 1
4th floor meeting room (A-401)
🕑 Time
Mondays at 6 pm
💬 Open to Everyone
feel free to join any meetup that sounds interesting to you.
Note on Background Knowledge: While we don’t require you to know a lot about AI Safety, our current events are targeted towards people who are already familiar with the basics of Machine Learning / AI Safety (e.g., having taken an AI Safety Fundamentals course by BlueDot or read about it). At the start of the next semester, we will have more beginner-friendly events as well.
Does this sound interesting to you?
Get Involved!
Want to present a paper, lead a discussion, or simply learn more about AI safety? We’d love to hear from you!
Make suggestions!
👉 Let us know what topics/papers you want to discuss or sign up to present you research.
Connect with us!
👉 Join our WhatsApp group for updates on upcoming events.
Learn more!
👉 Check out our resources for an introduction to AI safety topics.
New to AI Safety or Tübingen?
👉 Reach out if you’d like to schedule a one-on-one meeting with one of our organizers. We invite you for a coffee and can give you targeted advice! ☕️
Past Events
| 23.03.2026 | [Paper Discussion] Legal Alignment for Safe and Ethical AI by Kolt et al. (2026) |
| 16.03.2026 | [Talk] by Daniel Tan, Topics on AI Personas |
| 09.03.2026 | [Paper Discussion] “Who’s in Charge? Disempowerment Patterns in Real-World LLM Usage” by Sharma et al. (2026) https://arxiv.org/pdf/2601.19062 |
| 02.03.2026 | [Talk] “From Machine Psychology to AI Safety: Studying Deception, Emergent Misalignment, and Self-Awareness in LLMs” by Thilo Hagendorff (Group Leader at University of Stuttgart) |
| 23.02.2026 | [Social] Speed-Friending & What are you working on? Feel free to prepare a slide talking about what you are currently working on or what your research interests are! This event is also suited for people rather new to AI Safety! You are also welcome if you haven’t attended previous meet-ups 🙂 |
| 16.02.2026 | [Social] Casual Dinner @ Irish Pub Tübingen |
| 09.02.2026 | [Talk] by David Schmotz on SKILL-INJECT: Measuring Agent Vulnerability to Skill File Attacks |
| 02.02.2026 | [Talk] by Jeanne Salle on Measuring and Forecasting Autonomous Capabilities (if you want to read something beforehand, you can check out this blog post) |
| 26.01.2026 | [Paper Discussion] Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment |
| 19.01.2026 | [Paper Discussion]🫘 Spilling the beans – Teaching LLMs to Self-Report Their Hidden Objectives and its predecessor paper 💬 Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning |
| 12.01.2026 | [Paper Discussion] Activation Orcales: Training and Evaluating LLM as General-Purpose Activation Explainers |
| 15.12.2025 | Intro to Scalable Oversight by Ameya Prabhu (Bethgelab) |
| 01.12.2025 | Quick introduction + discussing Anthropic’s recent paper on “Natural Emergent Misalignment in Production RL” |