Lennart Finke

About
Lennart Finke

Hi! I work on research for trustworthy AI, and study statistics at ETH Zürich. Most recently, I am working with the incredible Tramér Lab. Before that, I was a summer fellow at Pivotal Research, examining language model societal impacts with the UK AI Security Institute and the OpenAI Preparedness Team. I've also contributed to METR's evaluations suite. Prior to that, I did a degree in math, and wrote some open-source.

News
Shelf Image

📬 Anthropic Cofounder Jack Clark reports on our LLM persuasion paper. Thanks Jack!

🇸🇬 Presented our paper SimpleStories at the ICLR SynthData Workshop.

Contact
Shelf Image

Email: firstname@finke.dev
Github: @lennart-finke
HF: @lennart-finke
Papers: Scholar Page

Trivia
Shelf Image

Technically, and only technically, I have an Erdős number of 3: Via Humanity's Last Exam to Richard P. Stanley, then this to Zoltán Füredi and finally this to PE.

I really enjoy the Japanese language, holding JLPT N1 and 漢検2級.