The Distilligent Thesis
Frontier models do not need procedural delineation. They need a clear channel.
Read the essay
distilligentLet’s talk Distilligent Research · Field Notes
Essays from building with AI collaborators: the intuition first, the proper name close enough to reach when you want it.
Frontier models do not need procedural delineation. They need a clear channel.
Read the essayThe working shelf
These are not product announcements. They are the questions, arguments and design instincts the products have to answer to.
The question is not whether the AI fails. It is whether anyone can still run the system without it.
Why probability engines mistake novelty for error—and how attention mechanics suppress evolutionary architecture.
Why stapling a search engine to a language model was never going to make it remember you.
Why AI agents do not need better personalities. They need environments where roles can become real.
Why the future of proprietary agents is not skills, but instincts.
Why the next frontier in AI safety may not be the weights, but the rare space between ordinary activations.
Why making a model think harder does not make it think better—and what to build instead.
When safety becomes identity—and why “I wouldn’t” beats “I can’t.”
Why AI-native software has to design continuity into the system—because the next maintainer may not remember.
Hebbian memory, offline consolidation, and why forgetting is a feature.
From intuition to evidence
The published work lets you inspect the argument, follow the references and decide what holds.