Trace

Alexander Turner

organization

Technical AI safety research

Received
$436,461
from 1 funders
Grants
6
Funders
1
Years active
2019–23

Grants over time

$0$200K$400K$600K20192020202120222023

Biggest funders

Long-Term Future Fund$436,461100%6

Grants received

DateFunderViaAmountCauseSourcePurpose
Apr 2023Long-Term Future FundEA Funds$30,000Interpretabilityea_fundsThis grant provides 5 months of funding for office space for collaboration on interpretability/model-steering alignment research
Apr 2023Long-Term Future FundEA Funds$40,000Interpretabilityea_fundsConference publication of interpretability and LM-steering results
Jan 2023Long-Term Future FundEA Funds$220,000Interpretabilityea_fundsYear-long salary for shard theory and RL mech int research
Jan 2023Long-Term Future FundEA Funds$115,411Interpretabilityea_fundsGeneral support for Alexander Turner and team research project - Writing new motivations into a policy network by understanding and controlling its internal decision-influences
Jan 2022Long-Term Future Fund$1,050Foundationsvipul_donationsThe grants database gives the following intended use of funds: "Ad campaign for "Optimal Policies Tend To Seek Power" to ML researchers on Twitter"
Mar 20, 2019Long-Term Future Fund$30,000Foundationsvipul_donationsGrant for building towards a “Limited Agent Foundations” thesis on mild optimization and corrigibility. Grantee is a third-year computer science PhD student funded by a graduate teaching assistantship; to dedicate more attention to alignment research, he is applying for one or more trimesters of funding (spring term starts April 1).