Tilman Räuker
AI Alignment Research
Some of my projects:
Understanding search in transformers
Notes on AI safety papers I read: @safe_paper
Technical AI safety Research Manager at ERA 2023
Toward Transparent AI was accepted at SaTML 2023
Participated at ARENA, an Alignment Research Engineer Accelerator
Co-organized the EAGxBerlin 2022
Thesis: On Temporally-Extended Reinforcement Learning in Dynamic Algorithm Configuration