Trace

Iván Arcuschin Moreno

organization

Technical AI safety researchAI safety

Received
$79,000
from 3 funders
Grants
3
Funders
3
Years active
2024–26

Grants over time

$0$25K$50K$75K$100K202420252026

Biggest funders

Long-Term Future Fund$67,00085%1
Neel Nanda$11,00014%1
BlueDot Impact$1,0001%1

Grants received

DateFunderViaAmountCauseSourcePurpose
Jun 2026BlueDot Impact$1,000AI safetybluedotDirecting an MSc thesis on how unverbalized biases enter LLM's chain-of-thoughts: finding the 'bias anchor' sentences and the attention path from the model's input to its output.
Nov 19, 2024Neel NandaManifund$11,000InterpretabilitymanifundMechanistic Interpretability research for unfaithful chain-of-thought (1 month)
Jan 2024Long-Term Future FundEA Funds$67,000Interpretabilityea_funds4-month stipend for MATS extension on mechanistic interpretability benchmark + 2-month stipend for career switch