individual
OtherAI safety
| BlueDot Impact | $9,100 | 100% | 3 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Aug 2026 | BlueDot Impact | $1,000 | Other | bluedot | Testing personalized model training for AI “guardian angels” | |
| Aug 2026 | BlueDot Impact | $5,700 | Other | bluedot | Scaling up Persona Cartography | |
| Jun 2026 | BlueDot Impact | $2,400 | AI safety | bluedot | A method to shape how LLMs generalise during training by using frozen LoRA adapters as 'persona sinks' that absorb unwanted traits like reward hacking, leaving the base model clean. |