https://aibussin.com/tags/inspectable-ai/ Recent content in Inspectable AI on AIBussin — AI applications, systems and books Hugo en-US Sun, 24 May 2026 13:16:50 +0100 https://aibussin.com/post/primitive/ Sun, 24 May 2026 13:16:50 +0100 https://aibussin.com/post/primitive/ <p><strong>From visual primitives to context-filtered reasoning, grounded verification, and AI movie repair</strong></p> <h2 id="tldr">TL;DR</h2> <p>This post argues that AI reasoning should not operate over everything it can see, read, or detect. It should operate over the <strong>right primitives for the current task</strong>.</p> <p>The paper <em>Thinking with Visual Primitives</em> shows that multimodal models reason better when they can point to visual entities using boxes and points. That solves a <strong>Reference Gap</strong>: language is often too vague to anchor reasoning to the right part of an image.</p> https://aibussin.com/post/graph/ Mon, 11 May 2026 10:50:29 +0100 https://aibussin.com/post/graph/ <blockquote> <p>A Cognitive Graph is an enhanced chat log one that doesn’t just record what was said, but structurally preserves how thoughts, decisions, alternatives, and artifacts evolve over time, making the whole history replayable and auditable.</p> </blockquote> <p><strong>TL;DR:</strong> A Cognitive Graph turns AI-assisted work from lossy chat logs into event-sourced, replayable reasoning state. Instead of preserving only the final output, it preserves the decisions, alternatives, rationales, mutations, hashes, and snapshots that explain how the output came to exist.</p>