Samuel Ratnam individual
Other AI safety Technical AI safety research
Received $10,050 from 1 funders
Grants 4
Funders 1
Years active 2026 Grants over time $0 $5K $10K $15K 2026
Grants received 4 · $10,050 · $2,513 average Date ↓ Funder Via Amount Cause Source Purpose Sep 2026 BlueDot Impact $950 Technical AI safety research bluedot Attending EA Global New York to seek support for AI safety research Aug 2026 BlueDot Impact $1,000 Other bluedot Testing personalized model training for AI “guardian angels” Aug 2026 BlueDot Impact $5,700 Other bluedot Building an open zoo of 134 personality-trained model organisms 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.
Grants made 1 · $80 · $80 average