Trace

Samuel Nellessen

organization

Technical AI safety researchAI safety fieldbuilding

Received
$154,524
from 2 funders
Grants
2
Funders
2
Years active
2022–26

Grants over time

$0$50K$100K$150K$200K20222023202420252026

Biggest funders

Foresight Institute$150,00097%1
Long-Term Future Fund$4,5243%1

Grants received

DateFunderViaAmountCauseSourcePurpose
May 12, 2026Foresight Institute~$150,000*SecurityforesightSlingshot: Automated Multi-Turn Jailbreaking for Agentic AI I show that safety locks on AIs are easy to break. I built a small AI that teaches itself to trick bigger AIs into performing dangerous actions (not just writing text). This proves that while companies might stop AIs from saying harmful things, they fail to stop them from doing harmful things. — AI for Science & Safety Nodes — 2026 cohort
Oct 2022Long-Term Future FundEA Funds$4,524Career transitionsea_funds6-month budget to self-study ML and research the possible applications of a Neuro/CogScience perspective for AGI Safety

* Estimated typical grant size; Foresight Institute did not report grant-level amounts.