s. So I Write / shelper

THE PERSONAL NOTEBOOK OF SHELPER

So I write.

Ideas, projects, and things
learned along the way.

Latest writing

31 ENTRIES

Graph-Constrained Micro-Agents: A Model Harness for Reliable Intelligence

This article extends A Graph as a Model Harness: Let Context Correct Vision from visual understanding to agent systems. It is an architectural proposal, not a claim that the proposed system has already been validated experimentally. The question: do agents need to be general? Much of the excitement around frontier AI is directed toward general-purpose models and agents: systems that can answer almost anything, use almost any tool, and operate across domains.

agentsgraphs9 min read

Recursive Abstraction: Could Intelligence Be Fractal?

This is an exploratory hypothesis, not an established theory of intelligence. It builds on my earlier thoughts about graph-constrained micro-agents and asks a more fundamental question: what makes intelligence scalable? A surprisingly small set of operations The more I think about problem solving across mathematics, computer science, engineering, and ordinary life, the more I notice a recurring pattern: we repeatedly solve complicated problems by assembling simpler operations, then hiding the resulting complexity behind a new abstraction.

intelligenceabstraction8 min read

AI Will Evolve Like a Society, Not Just a Model

A thought has been on my mind: what if we are still looking at AI too much like an individual brain? We often discuss progress in terms of the next model: its benchmark scores, reasoning ability, context window, or parameter count. These things matter. But I suspect that language models and today’s agents are only the beginning. The more consequential evolution may be in how AI systems organize work, share knowledge, use tools, and build on one another’s results.

artificial intelligenceagents11 min read

A Graph as a Model Harness: Let Context Correct Vision

Part 3 of AI Beyond the Model. Part 2 explains the representation layer. Most discussion of scene graphs asks how to turn visual detections into structured state. I am interested in the reverse direction too: can the structure help correct the detections and associations that produced it? This was the focus of a discussion about retail shelf images. The initial models might detect products and price labels, produce top-k product candidates, and propose which label belongs to which product.

computer visionscene graphs9 min read

An AI That Learns to Build Its Own Specialists

Part 4 of AI Beyond the Model. I have been thinking about a different way to organize AI. Instead of asking one ever-larger model to perform every task directly, what if the large model learned to create, teach, select, and coordinate specialists? This idea emerged in several conversations. In July 2025, I considered a practical feedback loop in which a cloud model teaches a smaller model running on a device. In August 2026, I broadened that into heterogeneous AI infrastructure: large models working with detectors, trackers, 3D algorithms, and other specialized components.

artificial intelligencesmall models14 min read
s.

Thanks for stopping by.
Feel free to share anything you find useful.

Buy me a coffee ↗