SafePlanBench: evaluating a Guaranteed Safe AI Approach for LLM-based Agents
$2K
Source
Notes
[Technical AI safety, AI governance] Seeking funding to develop and evaluate a new benchmark for systematically assesing safety of LLM-based agents
Other Grants by Manifund
376| Grant | Funder | Recipient | Amount | Date |
|---|---|---|---|---|
| Train great open-source sparse autoencoders | Manifund | Tom McGrath | $4K | May 2024 |
| Develop an accessible, low-cost system for single-cell imaging in multiple regions of freely moving organisms | Manifund | Andrew Luskin | $25K | Feb 2024 |
| Interpretable Forecasting with Transformers | Manifund | Sheikh Abdur Raheem Ali | $602.5 | Feb 2023 |
| Forethought | Manifund | Amrit Sidhu Brar | $365K | Dec 2025 |
| Luthien | Manifund | Jai Dhyani | $170K | Mar 2025 |
| Investigating the Effects of IF in the reversal of Type 2 Diabetes Mellitus. | Manifund | Ambreen Deol | $9K | Mar 2024 |
| Connect For Animals: a platform for ending factory farming | Manifund | Steven Rouk | $21K | Aug 2024 |
| Split Personality Training | Manifund | Florian Dietz | $3K | Apr 2025 |
| Holly Elmore organizing people for a frontier AI moratorium | Manifund | Holly Elmore | $5K | Jul 2023 |
| Lead-acid battery recycling in Philippines | Manifund | Micaella Rogers | $50K | Oct 2025 |
Showing 10 of 376 grants