Archive
Papers we have discussed, talks we have hosted and socials we have enjoyed so far.
Past events
Social
Summer social at Neckawa!
Paper discussion
AI Welfare: Is it bullshit or should we take it seriously?
Jeanne Salle
Talk
AI Control: Overview and ResearchArena paper
Lena Libon
Social
AI Safety Pubquiz
Talk
Models That Know How Evaluations Are Designed Score Safer
Katharina Deckenbach
Paper discussion
Europe2031 – What getting AI wrong means for us
Talk
Unlearning as an Asymmetric Generalization Problem
Amit Peleg
Social
Watchparty – The AI Doc: Or how I became an Apocaloptimist
Event
MATS Q&A with three recent MATS alumni
Talk
Claudini: Autoresearch Discovers State-of-the-Art Adversarial Attack Algorithms for LLMs
Alexander Panfilov
Social
AI Calibration Game
Paper discussion
Claude Mythos System Card
Talk
Compute Governance
Yannick Mühlhäuser (FLI)
Paper discussion
Paper discussion
The Artificial Self: Characterising the landscape of AI identity
Douglas et al. (2026)
Talk
AI Personas
Daniel Tan
Paper discussion
Who’s in Charge? Disempowerment Patterns in Real-World LLM Usage
Sharma et al. (2026)
Talk
From Machine Psychology to AI Safety: Studying Deception, Emergent Misalignment, and Self-Awareness in LLMs
Thilo Hagendorff (Group Leader at University of Stuttgart)
Social
Speed-Friending & What are you working on?
Social
Casual Dinner @ Irish Pub Tübingen
Talk
SKILL-INJECT: Measuring Agent Vulnerability to Skill File Attacks
David Schmotz
Talk
Paper discussion
Alignment Pretraining: AI Discourse Causes Self-Fulfilling (Mis)alignment
Paper discussion
Spilling the beans – Teaching LLMs to Self-Report Their Hidden Objectives, and its predecessor: Teaching Models to Verbalize Reward Hacking in Chain-of-Thought Reasoning
Paper discussion
Activation Oracles: Training and Evaluating LLMs as General-Purpose Activation Explainers
Talk
Intro to Scalable Oversight
Ameya Prabhu (Bethgelab)
Paper discussion
Quick introduction + Natural Emergent Misalignment in Production RL (Anthropic)