Research Engineer
Atul Saxena
I build the environments models are trained in, and the tools that show what they learned.
- RL Systems
- Interpretability
- ML Infrastructure
Research Engineer
Atul Saxena
I build the environments models are trained in, and the tools that show what they learned.
Tiny installable behaviour patches for frozen language models
A portable file format and runtime for reversible activation-space interventions. No fine-tuning, no weight modification, no prompt injection, no hosted service.
Changing a model’s behaviour normally means fine-tuning it (gigabytes, permanent, not adjustable at runtime) or prompt engineering (costs context on every single call, and is crude). Neither is removable mid-session or continuously dialable.
status: Verified infrastructure, honest negative result on the example patch