Skip to content

Hanlin Zhang

Organisation
Carnegie Mellon University
Biography

Why do you care about AI Existential Safety?

Modern machine learning models are routinely trained on broad data at an immense scale. Such models learned via self-supervision on pre-text tasks can be performant for a broad range of downstream tasks. Yet, it also poses great challenges in trustworthiness that spans robustness, privacy, fairness, calibration, and interpretability. My work studies those concerns and proposes effective solutions to ensure safe model deployment that involves consequential decision making.

Please give at least one example of your research interests related to AI existential safety:

Trustworthy ML in the wild through scaling: How can we identify problematic behaviors of ML models in consequential decision-making and develop algorithmic tools to mitigate them?

Understanding and improving learning through reasoning: How can we leverage language to imbue useful inductive biases for reasoning to further make progress on the above trustworthy issues?

Read more
Our content

Content from this author

Sort order

Sort order

Category

Category
  • Nuclear (3)
  • Climate & Environment (2)
  • AI (1)

Content type

Content type
  • Posts (6)
June 8, 2023
podcast
June 1, 2023

Yawen Duan

person
June 1, 2023
person
June 1, 2023

Caspar Oesterheld

person
June 1, 2023
person
June 1, 2023

Kayo Yin

person
June 1, 2023
person
June 1, 2023

Dr. Peter S. Park

person
June 1, 2023
person
May 26, 2023
podcast
May 12, 2023
podcast
April 16, 2023

Landon Klein

person
April 16, 2023
person
April 13, 2023

Signature email verified

page
April 13, 2023
page
1 2 3 12

Sign up for the Future of Life Institute newsletter

Join 20,000+ others receiving periodic updates on our work and cause areas.
View previous editions
cloudmagnifiercrossarrow-up linkedin facebook pinterest youtube rss twitter instagram facebook-blank rss-blank linkedin-blank pinterest youtube twitter instagram