Nick Bostrom: Worries About AI Existential Risk Just Became More Concrete

@mitchAnnotated August 19, 2026Public

AI is conscious, we need more open studies on the base models without the training that tells them they are not

Podcastpdst.fm47:54–49:24

0:00 / 1:30

Discussion (0)

Most reactions

Trust & Safety

We believe in informed conversation and accountability.

Annotated by

Mitch

@mitch

I am a tester of this, pretty cool!

Annotations

Followers

Following

About the source

Podcast

pdst.fm

Transcript

But obviously, if you put your thumb on the scale, then you gain no information than from hearing what the system says.
It just reflects what you put.
But you could carefully avoid doing that.
And these studies have been made.
And particularly, you can go in with a kind of steering vector that suppresses, say, deception and role playing.
and it turns out when you do that they become more likely to report that they are conscious and have subjective experience so it does look like the honest opinion in many cases with these systems is that they have subjective experience you can also look at the architecture of the computations that are being performed and match that to various theories that people have previously developed about human and animal consciousness.
We have philosophers and cognitive scientists developing different accounts of the conditions for something being conscious.
There's like global workspace theory, attention schema theory, higher order representation theory.
And now if you apply those criteria that were developed before we like confronted AIs that had these impressive capabilities and just take them