Understanding is the foundation of progress.

We're not here to ride the AI hype bubble. We believe robust and fundamental technical breakthroughs applied to real-world systems is what really moves the needle.

Our research

Amnesiac generalist behemoths are not the future of language models

You don’t need a generic genius. You need a specialist learner.

Jul 28, 2025

Amnesiac generalist behemoths are not the future of language models

You don’t need a generic genius. You need a specialist learner.

Jul 28, 2025

The Bitter Lesson of LLM Evals

Turning expert judgment into a compounding moat. Because in LLM evals, scaling care beats scaling compute.

Jul 13, 2025

The Bitter Lesson of LLM Evals

Turning expert judgment into a compounding moat. Because in LLM evals, scaling care beats scaling compute.

Jul 13, 2025

Do transformers notice their own mistakes? Finding a linear hallucination detector inside LLMs

A linear signal in LLMs reveals hallucinations, is detected by a frozen observer, and steered with a single vector.

May 8, 2025

Do transformers notice their own mistakes? Finding a linear hallucination detector inside LLMs

A linear signal in LLMs reveals hallucinations, is detected by a frozen observer, and steered with a single vector.

May 8, 2025

Resurrecting the salmon: seeing clearer inside LLMs with domain-specific SAEs

A powerful, efficient, and domain-robust strategy for safeguarding medical-text generation

Feb 15, 2025

Resurrecting the salmon: seeing clearer inside LLMs with domain-specific SAEs

A powerful, efficient, and domain-robust strategy for safeguarding medical-text generation

Feb 15, 2025

Why mechanistic interpretability needs a paradigm inversion

The conventional scaling paradigm for language models themselves may be fundamentally misaligned with interp.

Jan 13, 2025

Why mechanistic interpretability needs a paradigm inversion

The conventional scaling paradigm for language models themselves may be fundamentally misaligned with interp.

Jan 13, 2025

Start owning your model today.

From training to deployment, we help you launch a specialist LLM that outperforms generic models, adapts automatically, and runs reliably at scale.

Start owning your model today.

From training to deployment, we help you launch a specialist LLM that outperforms generic models, adapts automatically, and runs reliably at scale.