organization · Professor David Bau
Technical AI safety research
| Coefficient Giving | $1,773,217 | 70% | 3 |
| FTX Future Fund | $765,805 | 30% | 1 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| May 2024 | Coefficient Giving | Northeastern University | $1,095,017 | Interpretability | coefficient_giving | Large Language Model Interpretability Research (David Bau) |
| Sep 2023 | Coefficient Giving | Northeastern University | $116,072 | Interpretability | coefficient_giving | Mechanistic Interpretability Research (David Bau) |
| Nov 2022 | Coefficient Giving | Northeastern University | $562,128 | Interpretability | coefficient_giving | Large Language Model Interpretability Research (David Bau) |
| 2022 | FTX Future Fund | $765,805 | Interpretability, Evals | ftx_future_fund | This 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 |