Trace

David Bau

organization · Professor David Bau

Technical AI safety research

Received
$2,539,022
from 2 funders
Grants
4
Funders
2
Years active
2022–24

Grants over time

$0$500K$1.0M$1.5M202220232024

Biggest funders

Coefficient Giving$1,773,21770%3
FTX Future Fund$765,80530%1

Grants received

DateFunderViaAmountCauseSourcePurpose
May 2024Coefficient GivingNortheastern University$1,095,017Interpretabilitycoefficient_givingLarge Language Model Interpretability Research (David Bau)
Sep 2023Coefficient GivingNortheastern University$116,072Interpretabilitycoefficient_givingMechanistic Interpretability Research (David Bau)
Nov 2022Coefficient GivingNortheastern University$562,128Interpretabilitycoefficient_givingLarge Language Model Interpretability Research (David Bau)
2022FTX Future Fund$765,805Interpretability, Evalsftx_future_fundThis regrant will support several research directions in interpretability for 2-3 years, including: empirical evaluation of knowledge and guessing mechanisms in large language models, clarifying large language models’ ability to be aware of and control use of internal knowledge, a theory for defining and enumerating knowledge in large language models, and building systems that enable human users to tailor a model’s composition of its internal knowledge. — Artificial Intelligence