Synthetic Users Are Hypotheses, Not Participants
AI personas can widen a design team’s hypotheses, but fluent simulation is not lived evidence. Compare synthetic predictions with real observations before using them to decide.
Explore, Understand, Shape: A Knowledge Map for Humans and AI
Alkemata opens its Knowledge Map preview on 3 October 2026: a visual landscape for exploring connected topics, building understanding with AI and turning discoveries into action.
Alkemata for AI: What Capsules, llms.txt and MCP Are Actually For
Alkemata now exposes articles to AI in several different ways. Here is when a normal webpage is enough, what capsules add, how llms.txt and MCP differ, and how readers and…
An AI Memory Should Come with an Expiry Date
Persistent AI memory saves repetition but can preserve stale assumptions. Build a Memory Boundary Card to govern purpose, source, correction and expiry.
Do Not Make Human–AI Agreement the Goal
Human–AI agreement can hide anchoring or stubbornness. A better workflow preserves both provisional views, examines divergence and records why judgement changed.
From Reading to Doing: Alkemata’s Capsule Experiment
Alkemata proposes portable capsules that combine ideas, evidence and practical workflows, helping readers use their own LLMs to build projects and return experience to shared knowledge.
A Social Network Designed to Leave You Alone
What if an online network protected attention instead of consuming it—and measured success by the understanding, trust and work that continued after people logged out?
A Judge May Use an AI Draft—but Cannot Borrow Its Reasons
AI can assist judicial preparation, but a judge must still verify the record and law, resist anchoring, protect confidentiality and own every material reason.
What Makes an AI Answer Verifiable?
A citation is only the first step. Verifiable AI answers expose supporting passages, assumptions, calculations, provenance and a path to independent confirmation.
From Textbook to Personal Research Tutor: How LLMs Can Transform the Learning of Advanced Physics
How large language models can create adaptive physics courses, generate responsive exercises, and organize a personal scientific knowledge database—without replacing verification, mathematical discipline, or human judgment.