Longterm Wiki

Discovering latent goals (mechanistic interpretability PhD salary)

$2K
Funder
Recipient
Lucy Farnik
Program
Date
Jul 2023
Source
Notes

[Technical AI safety] 6-month salary for interpretability research focusing on probing for goals and "agency" inside large language models

Other Grants by Manifund

376
Showing 10 of 376 grants

Other Grants to Lucy Farnik

1
Discovering latent goals (mechanistic interpretability PhD salary) | Grants | Longterm Wiki