Stories, deep-dives and updates from the The Curator team.
How to Build an AI Change Detector That Reads Only What Changed
A practical guide to replacing repetitive document review with a change-aware pipeline that detects meaningful revisions, restores context, classifies impact, and routes only consequential changes to people.
Read post
Three Myths About Confidential Computing That Limit Private AI
Confidential computing is often described as encryption for data in use. That is accurate, but incomplete. Its real value—and its limits—emerge when we examine trust boundaries, attestation, model protection, and the software surrounding secure hardware.
Read post
Field Notes on Inference-Time Search: AI Is Beginning to Spend Compute on Decisions, Not Just Answers
The next shift in applied AI is not simply larger models or longer prompts. Systems are increasingly generating alternatives, testing them, and allocating inference compute according to the difficulty and consequence of each decision.
Read post
Durable Execution: How to Make AI Agents Survive Crashes, Timeouts, and Human Delays
A practical guide to durable execution: the workflow architecture that lets an AI agent pause, recover, retry safely, and continue without repeating consequential work.
Read postTool Calling: A Beginner’s Guide to Turning AI Responses Into Reliable Actions
A practical orientation to tool calling: the mechanism that lets language models query databases, invoke APIs, and operate software without confusing a proposed action with an executed one.
Read postInside KV Caching: How AI Models Remember a Conversation Without Rereading Every Word
KV caching is the hidden state that makes token-by-token generation practical. Here is how it works, why it consumes so much memory, and where newer cache designs must compromise.
Read postEvent-Driven Agents vs. Scheduled Agents vs. Continuous Agents: Which Operating Model Fits the Work?
AI agents do not merely need tools and instructions; they need an operating rhythm. Compare three architectures for deciding when an agent should wake, act, wait, and stop.
Read postHow to Build an AI Agent Permission Map Before You Grant Tool Access
A practical method for translating an AI agent’s job into narrow permissions, explicit approval gates, and testable controls—before it can act on real systems.
Read postThree Myths About Digital Twins That Hide Their Most Valuable Use
Digital twins are often described as perfect virtual replicas, elaborate 3D models, or infrastructure reserved for industrial giants. Each claim contains a fragment of truth—and each directs attention away from the real opportunity: decision-making under changing conditions.
Read postWhat The Curator blog is for
How it differs from the library
The library is the slow layer: ideas, methods and histories that should still read well next year. The blog is where the current argument lives — a launch worth interrogating, a strategy that keeps failing quietly, a piece of research that changes how a familiar problem looks. Posts argue; library entries explain.
Publication is paced rather than bulk-loaded, and every post is written specifically for this site, not shared across the sibling publications.
Editing and corrections
Posts are bylined and dated, and material post-publication changes are noted on the page rather than made quietly. Any reader can file a correction from an article page; the ones that check out are applied and credited.
External claims link to their source so readers can verify rather than trust. Our methodology page describes precisely where AI assists in drafting and where human editorial judgement is required before anything is published.
How the notebook differs from the archive
Two different jobs
The archive holds the durable essays. The notebook is for shorter, more provisional writing — what a new release changed about a convention, a myth worth puncturing, the reasoning behind a product decision.
Keeping them apart lets a field note stay tentative without diluting the archive, and lets an essay take months without missing the conversation entirely.
Cadence and authorship
Posts are paced rather than bulk-published, and each is written for this site specifically — nothing is syndicated from the sibling publications. Every post is bylined and dated, with an author page collecting that writer's work.
Comments, ratings and correction requests are open on every post and moderated for spam and abuse only. Disagreement about a reading is the entire point.
Corrections here too
A post that turns out to be wrong is corrected on the page, with the change noted where it alters meaning. Nothing is quietly removed to tidy the record.
External claims link out so you can check them, and a rotted link is a correction like any other — report it and it gets replaced.