individual
AI safety fieldbuildingTechnical AI safety research
| BlueDot Impact | $1,400 | 100% | 2 |
| Date ↓ | Funder | Via | Amount | Cause | Source | Purpose |
|---|---|---|---|---|---|---|
| Jul 2026 | BlueDot Impact | $400 | Evals | bluedot | Finishing paper experiments on improving on BLOOM (Anthropics automated evals tool) by using logit steering, which improves elicitation rate while keeping transcripts natural/ non-jailbroken. | |
| Jun 2026 | BlueDot Impact | $1,000 | Training pipelines | bluedot | Finishing PhD on automating auditing of LLMs so it scales better. Currently extending Anthropic's BLOOM framework to increase elicitation of behaviours, looking into logit diffing and tree search. |