University in New York City whose researchers received a 2024 AI Safety Fund grant to evaluate and mitigate deceptive behaviour arising from reward hacking.
Show detailsHide details
Received $3.7M from 4 funders
’18
’19
’20
’21
’22
’23
’24
’25
’26
Checked 25 Oct 2026
Money flows
Where its money came from and where it went. Pick years and what to show; hover a box or ribbon for details, click one to focus it, click the background to see everything.
Funded by
All grants
7 grants totalling $3.7M, newest first.
2026 2 grants · $1.2M
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 19 Feb 2026 | The Alignment Project | ~$590k | Alignment Project round 1 (lead: Individual #34065): What Can Mr. Hyde Tell Us About Dr. Jekyll? Efficiently Evaluating and Red-teaming "Safe" Models with Unsafe Alter Egos. Amount undisclosed; awards £50k–£1M from a £27m pool across 60 announced projects. source |
| 19 Feb 2026 | The Alignment Project | ~$590k | Alignment Project round 1 (lead: Izmailov, Pavel): Weak-to-Strong Consistency Reinforcement Learning. Amount undisclosed; awards £50k–£1M from a £27m pool across 60 announced projects. source |
2024 1 grant · $250k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| Nov 2024 | AI Safety Fund (Frontier Model Forum) | ~$250k | AISF Round 1 (PI Individual #3270): deceptive behaviour arising from reward hacking. Amount undisclosed (grants were $150k–$400k); share of >$3M across 12 grants. Amount here is an estimate: an equal share of the round's >$3M. source |
2023 2 grants · $2M
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| Jun 2023 | Coefficient Giving | $1M | Project on language model alignment research — paid by Good Ventures Foundation on Open Philanthropy's advice, fiscal year Jul 2022–Jun 2023 (990-PF Part XIV 3a; payment in that year, not the grant total) source |
| Jun 2023 | Coefficient Giving | $966k | Project testing the truthfulness of AI systems — paid by Good Ventures Foundation on Open Philanthropy's advice, fiscal year Jul 2022–Jun 2023 (990-PF Part XIV 3a; payment in that year, not the grant total) source |
2021 1 grant · $250k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 2021 | MacArthur Foundation | $250k | Center on Race, Inequality and the Law: flexible support and AI/criminal legal system network (1 year, 6 months) — MacArthur Technology in the Public Interest, grantee page source |
2018 1 grant · $15k
| Date | Funder | Amount | Purpose |
|---|---|---|---|
| 2018 | MacArthur Foundation | $15k | X-Grant: workshop on litigating algorithmic decision-making systems (1 month) — MacArthur Technology in the Public Interest, grantee page source |