Writing
Articles from this site and the Anthus publications, newest first. Each one opens where it was published.
DeepSeek restrictions reach inside the tools
DHS's DeepSeek restrictions reach third-party tools, too. A separate poisoned-model experiment shows why knowing whose models are inside matters.
Pi 1.0, and the Durable Agent We're Building on It
Earendil shipped Pi 1.0 and an experimental companion, Pi Durable. Pi is one of the agents Kanbus dispatches tasks to, and we like Pi Durable so much that we're building a durable Pi agent platform into Chatticus.
It's Not a System 1 Model If It Takes Ten Seconds
Fastino's GLiDE beats every open model on our reasoning benchmark, but not Jev: less accurate, five times slower, ten times the cost, and a confidence that barely tells right from wrong.
The OpenAI Decisions API Needs a Confidence You Can Trust
We've routed decisions on LLM confidence since 2023, and calibration is what we most hope OpenAI's new Decisions API gets right. The model underneath, GPT-6 Luna, isn't there yet: on 3,600 reasoning problems its 99% meant 68%, and by five…
Can Averaging Reduce Noise in an AI Decision Model?
We asked Jev the same question ten times in one request and expected ten identical answers. They split, four votes to six. Kahneman, Sibony and Sunstein call that kind of variation noise. Averaging the copies didn't make Jev more accurate,…
Primus Is a Classifier Lab: Operationalizing Classifiers at Scale
A hosted decision model sat at 77 percent accuracy through 87 rounds of reviewer feedback, then one approved question took it to 87. Here is the loop that did it, every figure published, and the offer to run it on your judgment task.
DataParade
DataParade is a privacy and security product built on a semantic knowledge graph, with a custom ontology and taxonomy that ties into the OCSF standard. Anthus is working with DataParade to develop it. It belongs to the new class of tooling…
Decision Models Are Not Calculators
Jev chose one in every ordering of a fair-die question; Kev leaned toward one, and Laya overwhelmingly chose six. Benford's Law remains a hypothesis.
Text as an Image, Then a Magnifying Glass
Text as an Image, Then a Magnifying Glass: LensVLM compresses text by showing it to a vision-language model as an image, then opens the original text where the answer lives.
The Next Chatbot Is Growing on This Year's Compost
Chatbots learned from everything people wrote in public. Now brands are writing fake posts in public for the chatbots to read, so the next chatbot is trained on them and repeats them as if they were true.
The Button Marked Auto Has an Owner
Millions of programmers let a setting called Auto pick which AI answers them. Lately it keeps picking Grok, the one owned by Elon Musk, whose company also owns the program they are using, and who has shown little interest in checking which…
The End of the Rave
Castlemorton, 1992: thirty thousand people danced in a Worcestershire field for a week, and the night itself was the only version that counted. Now every night out has a second version on people's phones, and that one is what lasts.
No recent articles from this publication yet.
2026
2025
2024
2023
2012