AI Safety and Alignment Group
ELLIS Institute Tübingen · Max Planck Institute for Intelligent Systems
Group page · Updates · Datasets
AI safety · alignment · evaluation
We develop algorithmic approaches to reduce harms from increasingly capable general-purpose AI systems. Our work focuses on the alignment and evaluation of autonomous language-model agents, frontier-model risks and capabilities, and model generalisation and steerability.
The AI Safety course at the University of Tübingen is openly available.
Browse all repositories or follow the group on Substack.
Popular repositories Loading
-
PostTrainBench PostTrainBench Public
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
-
tue-ai-safety-course tue-ai-safety-course Public
AI safety course at the University of Tübingen (Summer Semester 2026)
-
skill-inject skill-inject Public
Skill-Inject: Measuring Agent Vulnerability to Skill File Attacks
-
InferenceBench InferenceBench Public
Benchmarking Open-Ended Inference Optimization by AI Agents
-
promptinject-agent-skills promptinject-agent-skills Public
Agent Skills Enable a New Class of Realistic and Trivially Simple Prompt Injections
-
decomposing-eval-awareness decomposing-eval-awareness Public
Decomposing and measuring evaluation awareness in existing benchmarks and our proposed EvalAwareBench.
Repositories
- inferencebench-site Public
- PostTrainBench Public
Measuring how well CLI agents like Claude Code or Codex CLI can post-train base LLMs on a single H100 GPU in 10 hours
- researcharena-website Public
- ResearchArena Public
- em-generalization Public
Top languages
Loading…
Most used topics
Loading…