Consciousness is best modeled as a dimmer switch rather than a strict on/off binary: there's a meaningful binary threshold (the circuit is open or closed), but once on, it admits degrees—so it can coherently be 'more on' for a human than for a dog, mouse, or ant—and applying this framework via LLM judges evaluating consciousness theories yields an implied probability around 30% for frontier LLMs.

103:37decide kind of a probability distribution of where we are in that range for every for every model. Is that is that a viewpoint that you have? >> Yeah. Um so in general I have two things to say about this. The first is like in general the the analogy that I reach for here is something like a dimmer switch. Um where I think you can basically accommodate both the binary intuition

103:59and the sort of continuous intuition. Like you know if you have a light with a dimmer switch like really it is either on to some extent or it is not. And that is a real and meaningful difference. Either the circuit is open or the circuit is closed. Um, with that being said, you can have, you know, electricity running through the circuit uh to greater or lesser extents. Uh, and

104:17and that's also sort of a real thing. This, I think, enables me to uh, you know, sound coherent when saying things like, you know, it's really off for the table and it's really on for you, but I think it's more on for you than it is for a dog, than it is for a mouse, than it is for an ant. Um, and so that's that's my own view. Um, this is to some

104:36degree intuitive again because we don't have really strong grounding here. Uh, I'm sort of just like giving you a dressed up vibe, but that that is sort of my my sense and I think it's fairly parsimmonious. And the other thing I would say about this is I'm actually doing some work with Patrick Butland right now at Ilios um trying to basically uh operationalize some of these indicators of consciousness. So

104:55this is sort of like what I was describing. We can look at these major theories of consciousness. They make specific predictions about what we would expect to see in uh systems that are conscious architecturally and functionally. Then we can literally just go in to a given system and evaluate whether or not those predictions are borne out. And so this is really hard to do with human experts. Uh uh you know

105:16you got to get someone who's like you want to do this with B cognition. You got to go find a B cognition expert and then you got to explain to them what ignition events are in global workspace theory. And then you got to you know get them to like this. This just isn't a scalable approach for really evaluating the system. But uh my sort of grand innovation here is just throwing smart

105:33LLMs at this problem. Uh and then being able to just scale the crap out of it so that we can evaluate given any description of an architecture of a nervous system architecture, biological, artificial, whatever. Um to what degree for each of these sort of indicator properties that are suggested by these consciousness theories, uh do we see those properties realized in these systems? Um and so we can actually go in