Currently Seeking Funding

I'm seeking grants to fund compute infrastructure for training interpretability-focused models. This research bridges interactive narrative design with mechanistic interpretability — a novel approach to understanding emergent AI behavior through human-readable structures.

$45k Primary Ask
12 mo Project Timeline
3+ Published Outputs

Storyworlds as Sparse Autoencoders

Interactive narratives encode compressed, interpretable representations of complex systems. A well-designed storyworld forces coherent structure onto agent behavior, goal dynamics, and world-state evolution — precisely the features we want to extract and understand in AI systems.

This research program tests whether models trained on richly-structured narrative data produce more interpretable internal representations than models trained on unstructured corpora, and whether SAE features extracted from such models map more cleanly to human-understandable concepts.

Narrative Structure
Structured Latents
Interpretable SAEs
Alignment Insights

Execution Timeline

Phase 1 — Months 1-2
Infrastructure & Data Preparation
Deploy GPU cluster. Curate and structure the 40M token corpus with narrative annotations. Prepare comparison datasets (unstructured web text, existing benchmarks).
Phase 2 — Months 3-6
Model Training
Train Intellect-3 variant on narrative-structured corpus. Train control model on matched unstructured data. Document training dynamics and emergent behaviors. Iterate on architecture choices.
Phase 3 — Months 7-10
SAE Extraction & Analysis
Extract sparse autoencoders from both models. Compare feature interpretability. Map features to narrative elements (agents, goals, world-states, causality). Build interactive exploration tools.
Phase 4 — Months 11-12
Publication & Open Source
Publish findings. Release model weights, SAEs, and training code. Document methodology for narrative-structured interpretability research. Community engagement.

Deliverables

Trained Models

Intellect-3 variant trained on narrative corpus + control model. Open weights released for reproducibility.

SAE Feature Analysis

Extracted autoencoders with annotated feature dictionaries mapping to narrative structures.

Research Paper

Peer-reviewable publication documenting methodology, results, and implications for interpretability.

Open Source Tools

Training scripts, data pipeline, and SAE extraction code for community replication.

Narrative Dataset

Curated 40M token corpus with structural annotations, released for future research.

Interactive Demo

Web interface for exploring SAE features and their narrative correspondences.

Budget

Funding primarily supports compute infrastructure. I'm based in Chile, which provides significant runway advantages — this budget goes further than equivalent US-based research.

Item Allocation
GPU Cluster (RTX 4090 x4 or equivalent) $16,000
Cloud compute overflow / experimentation $2,000
Infrastructure (storage, networking) $1,500
Miscellaneous (publication fees, tools) $500
Researcher stipend (12 months) $25,000
Total $45,000

Note: Chile-based, significantly lower cost of living than US/EU. Stipend enables full-time dedicated research.

Why Me

I bring a unique combination of deep technical experience and long-standing work at the intersection of interactive systems and AI. This isn't a pivot — it's the convergence of parallel research threads I've pursued for over a decade.

10+ yrs

Technical Development

Founded TradeLayer (2014), a Bitcoin-native derivatives protocol. Deep experience shipping production financial systems.

21 yrs

Interactive Narrative

Collaboration with Chris Crawford and game design community. Long-term research into storyworlds as computational structures.

13-17

Qubit Systems

Operating commercial quantum computing systems for semantic indexing. Provisional patents filed for QFT-based techniques.

40M+

Token Corpus

Built and maintained large-scale corpus with QFT-enhanced retrieval systems. Infrastructure ready for training.

Theory of Change

Current interpretability research struggles with the gap between mathematical feature descriptions and human-understandable concepts. Narrative structures provide a natural bridge — humans already think in terms of agents, goals, obstacles, and causality.

If this works:

We get a new methodology for interpretability research that produces more human-legible features. We get evidence for or against the hypothesis that training data structure shapes internal representation quality. We get open tools and models that other researchers can build on.

If this doesn't work:

We get valuable negative results about the limits of data-structure-driven interpretability. We still release the models, data, and tools for others to learn from. The failure modes themselves inform future research directions.

Let's Talk

I'm happy to discuss this research program in detail, answer questions about methodology, or explore how this work might complement your foundation's priorities.

Get in Touch