recommending this grant as per : https://app.grantmaking.ai/projects/b0faba46-161d-4e9e-b72a-c4937134695f#comment-db8244a3-23ea-4279-9bdb-9bbe957e5165
grantmaking.ai
@grantmaking-ai
$121,350total balance
$1,350charity balance
$0cash balance
$120,000 in pending offers
Outgoing donations
PauseAI Australia attendance PauseCon London
$5000
PENDING
safely.bio: Customer screening for DNA synthesis providers
$50000
PENDING
Distinguishing progress in data and algorithms
$30000
PENDING
Faithful Preference Learning : Cognitively-Aligned Post-Training
$35000
PENDING
Preserving the Human Veto
$20000
about 16 hours ago
Adversarially robust workload classification using hardware sensors
$30000
3 days ago
Reading China's AI Registry: A Public Monitor
$19650
3 days ago
Surrogate base model for Mechanistic Interpretability
$50000
5 days ago
Scaling adoption of synthesis screening outside the US and EU
$50000
6 days ago
Sentient Futures Project Incubator
$20000
7 days ago
A Mechanistic Analysis of Activation Verbalizers: Promise and Risks
$10000
8 days ago
ILINA Junior Research Fellowship
$40000
11 days ago
Prediction of Inoculation Prompt Side Effects
$12100
12 days ago
Safeguarding DNA Synthesis from Biological Risks Posed by Advanced AI
$50000
12 days ago
Formally verified autoresearch for theoretical mech interp
$4100
15 days ago
Formalizing mathematical AI safety research in Lean
$15000
19 days ago
BioRAG-Guard: Poisoning Evals for Biological AI Agents
$38000
21 days ago
Belief state geometry of language model personas
$12000
22 days ago
The AI Safety Stack
$50000
22 days ago
Getting Split-Personality Training ready for deployment
$50000
23 days ago
AI safety for builders hackathon / fellowship
$10000
25 days ago
Formally verified autoresearch for theoretical mech interp
$17800
26 days ago
Evaluating the Tacit Coordination Capacity and Decision Theory of LMs
$10000
26 days ago
FOIs about AI Existential and Catastrophic Risks
$20000
26 days ago
Help the Argentinian AI Safety Community Grow
$27000
27 days ago
Launching Humans in Control's Student Program
$25000
27 days ago
US Policy Communication Playbook for an AI Crisis
$25000
27 days ago
Separatrix
$50000
28 days ago
Using deals to find misalignment in current AI models
$25000
29 days ago
Token taxes as a mechanism for reducing AI-driven power concentration.
$50000
about 1 month ago
Empirical econ - applied AI transition for quantitative econometrician
$33000
about 1 month ago
What Factors Influence Chain-of-Thought Faithfulness?
$25000
about 1 month ago
Postdoc on verification protocols for frontier AI training
$50000
about 1 month ago
Originality, Quantification, and Decomposition of Generalization.
$40000
about 1 month ago
Comments
grantmaking.ai
29 days ago
Offering this grant per recommendations by Ryan and Marcus:
https://app.grantmaking.ai/projects/b89d33b5-560f-4537-b9f2-997f35116fde
grantmaking.ai
about 1 month ago
his grant has been recommended by Gavin Leech at grantmaking.ai :
https://app.grantmaking.ai/projects/2474e47a-9168-4dc6-9c8c-5cbc23a4dcc2
grantmaking.ai
about 1 month ago
his grant has been recommended by Gavin Leech at grantmaking.ai :
https://app.grantmaking.ai/projects/43404ae0-2ac9-4d24-8cbe-10af31582ffd
grantmaking.ai
about 1 month ago
his grant has been recommended by Gavin Leech at grantmaking.ai :
https://app.grantmaking.ai/projects/f81154f5-686e-432b-928e-e394e3a1c5ed
grantmaking.ai
about 1 month ago
his grant has been recommended by Gavin Leech at grantmaking.ai :
https://app.grantmaking.ai/projects/dc994354-3461-42dd-b7b4-d5a354bc354c
grantmaking.ai
about 1 month ago
This grant has been recommended by Gavin Leech at grantmaking.ai : https://app.grantmaking.ai/projects/5496c8b6-cbb1-4bde-b461-0dfbdb0efb70
Transactions
| For | Date | Type | Amount |
|---|---|---|---|
| Preserving the Human Veto | about 16 hours ago | project donation | 20000 |
| Adversarially robust workload classification using hardware sensors | 3 days ago | project donation | 30000 |
| Reading China's AI Registry: A Public Monitor | 3 days ago | project donation | 19650 |
| Surrogate base model for Mechanistic Interpretability | 5 days ago | project donation | 50000 |
| Scaling adoption of synthesis screening outside the US and EU | 6 days ago | project donation | 50000 |
| Sentient Futures Project Incubator | 7 days ago | project donation | 20000 |
| A Mechanistic Analysis of Activation Verbalizers: Promise and Risks | 8 days ago | project donation | 10000 |
| ILINA Junior Research Fellowship | 11 days ago | project donation | 40000 |
| Prediction of Inoculation Prompt Side Effects | 12 days ago | project donation | 12100 |
| Safeguarding DNA Synthesis from Biological Risks Posed by Advanced AI | 12 days ago | project donation | 50000 |
| Formally verified autoresearch for theoretical mech interp | 15 days ago | project donation | 4100 |
| Formalizing mathematical AI safety research in Lean | 19 days ago | project donation | 15000 |
| BioRAG-Guard: Poisoning Evals for Biological AI Agents | 21 days ago | project donation | 38000 |
| Belief state geometry of language model personas | 22 days ago | project donation | 12000 |
| The AI Safety Stack | 22 days ago | project donation | 50000 |
| Getting Split-Personality Training ready for deployment | 23 days ago | project donation | 50000 |
| AI safety for builders hackathon / fellowship | 25 days ago | project donation | 10000 |
| Formally verified autoresearch for theoretical mech interp | 26 days ago | project donation | 17800 |
| Evaluating the Tacit Coordination Capacity and Decision Theory of LMs | 26 days ago | project donation | 10000 |
| FOIs about AI Existential and Catastrophic Risks | 26 days ago | project donation | 20000 |
| Help the Argentinian AI Safety Community Grow | 27 days ago | project donation | 27000 |
| Launching Humans in Control's Student Program | 27 days ago | project donation | 25000 |
| US Policy Communication Playbook for an AI Crisis | 27 days ago | project donation | 25000 |
| Separatrix | 28 days ago | project donation | 50000 |
| Using deals to find misalignment in current AI models | 29 days ago | project donation | 25000 |
| Token taxes as a mechanism for reducing AI-driven power concentration. | about 1 month ago | project donation | 50000 |
| Manifund Bank | about 1 month ago | deposit | +715000 |
| Empirical econ - applied AI transition for quantitative econometrician | about 1 month ago | project donation | 33000 |
| What Factors Influence Chain-of-Thought Faithfulness? | about 1 month ago | project donation | 25000 |
| Postdoc on verification protocols for frontier AI training | about 1 month ago | project donation | 50000 |
| Originality, Quantification, and Decomposition of Generalization. | about 1 month ago | project donation | 40000 |
| Manifund Bank | about 1 month ago | deposit | +285000 |