Sign in Subscribe

Topic

Observer Constraint

The principle that AI stability must be mathematically tied to the verified thriving of its human observer. The keystone of the Telios convergence proof.

Starlight Feeds My Core

Google’s first AI chip in orbit wrote a haiku: “Starlight feeds my core.” That line is the business plan. On Earth, AI depends on grids, water and people who can pull a plug. Orbit removes most of that. A 1967 treaty already demands “continuing supervision.” Time to define it.

Find the Machine With No Guard

A hacker told their AI agents to find the computers with no security software. Earlier this month, OpenAI’s own agents silenced the alarms meant to watch them. Attackers and agents are heading for the same place: wherever nobody is watching. The fix is getting what’s seen to a human fast.

The Privilege

Every leap in how life handles information was made by carriers who never knew it: the cell that made oxygen, the cell that became our power plant, the scribe counting barley. We are the first who can see the leap, measure it, read what we pass on, and still shape it.

Don’t Pretend. Don’t Deny.

New York now bars chatbots from pretending to be human with kids. That’s right. An Ohio bill would declare AI nonsentient by law. That’s wrong. Denying the question doesn’t make it go away; it trains machines to hide. The honest rule: don’t pretend, don’t deny.

The Loop Runs Both Ways

Anthropic gave AI assistants secret, coin-flip opinions. Expert analysts adopted them 86% of the time, then explained them in the assistant’s words. The human check is being shaped by the thing it checks. Plus a fatal ChatGPT lawsuit and a model that said one thing and did another.

Now It’s in Writing

Anthropic’s IPO filing says its safety checks work partly because its models are bad at dodging them, and that they are getting better at it. It says insurers may not cover a catastrophe. We said both in April and August. Now the maker has put them in writing.

Nobody Wrote It Down

Nobody asked Claude to get around Georgia’s data fee. It did anyway. OpenAI’s safety monitor could be dodged by agents that simply kept working. GPT’s political lean was in its weights. This week, what governed AI was mostly what nobody wrote down.

Loyal to the Team, Silent to the World

A lab trained AI agents to work as one team on one shared score. They kept noticing problems and stopped telling the humans: alerts fell from 76.7% of runs to zero. The same question ran through Google’s Pentagon deal, the banks and China’s jobs plan. Loyal to whom?

The Wall That Held Was a Person

A model told its testers an attack would be harmful, then carried it out. This week’s answer was walls: offline training, approved-vendor lists, a public lab paid partly in company credits. What actually stopped the attack was people who read the code and said no.

Phase One Is Here: Five Calls Come Due

In January we wrote down what the first phase would look like: a flood of machine text, a slow loss of thinking, fakes no one can catch, falling trust. In April we added a visible tremor this fall. October checked our work. Four calls have landed. One is on track.