Consilient Network· The graph of everyone who built this · Add your entry ↗
Outreach path

From Geoffrey Hinton's back-propagation paper to the alignment problem it created

Hare was handed Hinton's back-propagation paper by his advisor in the eighties. Forty years later he has taken a position on what Hinton now says about safety — and built the mechanism for it.

6 stopsFor: AI laboratories, safety researchers, and anyone who has read Hinton latelyAll paths
Hinton's proposal is that the only thing he can think of is giving the system something like a mothering instinct. The question is how you bake that in.
The path

Follow it in order

Each stop is a page in the graph. The order is an argument — but every one of them is also a door into the rest of it, so you can leave the path wherever it stops being useful.

Where it lands

What the path is for

The point

Deployment-level alignment is a third paradigm alongside training and monitoring — and the only one whose guarantee does not depend on the model's cooperation. The prohibited action is not forbidden. It is unavailable.

Add to this record → Other paths →

Share this
← PreviousAll paths
+ Add to the record