individual
Technical AI safety research
| BlueDot Impact | $50 | 100% | 1 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Aug 2026 | BlueDot Impact | $50 | Alignment methods, Evals | bluedot | Testing whether RLVR (Olmo-3-7B-Think) vs RLHF (Llama-2-7B-chat) training produces different instrumental convergence rates, using InstrumentalEval benchmark with dual-judge LLM scoring. |