Jan Brauner
Researcher in the field of AI and language models
Best podcasts with Jan Brauner
Ranked by the Snipd community
Oct 3, 2023 • 7min
"How to Catch an AI Liar: Lie Detection in Black-Box LLMs by Asking Unrelated Questions" by Jan Brauner et al.
Jan Brauner, an AI researcher, discusses the development of a simple lie detector for language models. The lie detector uses unrelated follow-up questions and logistic regression. It is highly accurate and generalizes across different models and contexts. This indicates distinctive lie-related patterns in language models.
Mar 31, 2022 • 22min
Dr Jan Brauner - AI in Medicine & Clinical Research
Dr Jan Brauner, PhD candidate, discusses AI in medicine, clinical trials, and AI safety. Topics include career transitions from medicine to machine learning, characteristics for AI safety work, future goals in AI and medicine, and unconventional paths in medicine and clinical trials.
