organization
Technical AI safety research
| Foresight Institute | $100,000 | 100% | 1 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Feb 2024 | Foresight Institute | ~$100,000* | Security | foresight | Self-Other Overlap via Fine-Tuning — testing self-other overlap as a scalable method to reduce deception in RL agents and LLMs (initially listed as 'AE Studios'). Focus area: Neurotech. First listed on foresight.org/ai-safety by Feb 2024. — AI Safety Grants (Underexplored Approaches: Automation / Neurotech / Security / Multi-Agent) |
* Foresight Institute planned to give $2.5-3.2m over 26 grants in 2023 and 2024; estimating each at roughly the average grant size.