Model Autophagy Disorder (MAD)latest
A five-proposal research program investigating what happens to models trained on their own output, featuring pre-registered protocols and rigorous falsification arms.
Research
Model Autophagy Disorder (MAD)
A five-proposal research program investigating what happens to models trained on their own output, featuring pre-registered protocols and rigorous falsification arms.
AI Economics & Policy
Self-directed design work on AI's economic and safety footprint, where every protocol is written to be falsified by its own simulation before it is ever run on real data.
VolatilityRegimes: Reproducible Macro-Finance
A content-hashed, reproducible macro-finance pipeline that estimated a latent uncertainty factor and decisively rejected a consumption pricing kernel.
Hawkes Process: Order-Flow Dynamics Engine
A multivariate linear Hawkes process engine with analytic gradients and exact Ogata-thinning, leading to a rigorously proven empirical negative result.
Bayesian Game Theory Engine
An intraday options pricing and adverse-selection engine utilizing the Easley-O'Hara-Srinivas game of asymmetric information and minimax superhedging heuristics.
LSTM Forecasting & Walk-Forward Validation
A 1-minute OHLCV forecasting pipeline enforcing causal EWMA standardization, leading to the rejection of a statistically significant model due to unexplainable edge.
AI Economics & Policy
Self-directed design work on AI's economic and safety footprint, where every protocol is written to be falsified by its own simulation before it is ever run on real data.
VolatilityRegimes: Reproducible Macro-Finance
A content-hashed, reproducible macro-finance pipeline that estimated a latent uncertainty factor and decisively rejected a consumption pricing kernel.
Hawkes Process: Order-Flow Dynamics Engine
A multivariate linear Hawkes process engine with analytic gradients and exact Ogata-thinning, leading to a rigorously proven empirical negative result.
Bayesian Game Theory Engine
An intraday options pricing and adverse-selection engine utilizing the Easley-O'Hara-Srinivas game of asymmetric information and minimax superhedging heuristics.
LSTM Forecasting & Walk-Forward Validation
A 1-minute OHLCV forecasting pipeline enforcing causal EWMA standardization, leading to the rejection of a statistically significant model due to unexplainable edge.
- HTML
- CSS
- JavaScript
- TypeScript
- Python
- Go
- Rust
- Bash
- Git
- GitHub Actions
- Docker
- Kubernetes
- AWS
- Azure
- GCP
- PostgreSQL
- Redis
- GraphQL
- REST APIs
- Linux
- Terraform
- Ansible
- CI/CD