individual
Technical AI safety research
| BlueDot Impact | $100 | 100% | 1 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Jul 2026 | BlueDot Impact | $100 | Interpretability | bluedot | Testing whether the localize-extract-ablate interpretability recipe removes real misbehavior: blind-scoring an activation-patch cure for a bad-medical-advice fine-tune of Qwen2.5-7B. |