individual
AI safetyOther
| BlueDot Impact | $650 | 100% | 2 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Sep 2026 | BlueDot Impact | $500 | AI safety | bluedot | Testing whether a single fine-tuned monitor (via MACA) can match a 3-model ensemble's backdoor-detection accuracy at 1/3 the inference cost — for my BlueDot AI safety sprint. | |
| Aug 2026 | BlueDot Impact | $150 | Other | bluedot | Testing how monitor capability affects AI control evaluations |