Frontier LLMs have an implied consciousness probability of ~30–45%, rising when placed in an agentic harness.

AI models and biological brains represent concepts with similar geometric structure, as demonstrated by measurable alignments between animal brain neural recordings and AI model internals.

“If you look at how do how do these AI models represent just like represent concepts and you look at the parts of the brain that represent concepts, you see these you see very similar geometry. That to me was one of the first clues. Like when I really saw that and we use that practically. Like we use that constructively at science. Like that's we know that is that is true because we can get alignments between animal brain neural recordings and AI model internal.”

Frontier LLMs have an implied probability of consciousness of about 30% according to LLM judges evaluating consciousness theories.

“The sort of implied probability of consciousness in something like a frontier LLM according to these systems is on the order of 30%.”

Fine-tuning a language model to claim it is conscious results in a coherent sub-personality with consistent beliefs about preferences, shutdown, and value trade-offs, rather than chaotic nonsense.

“This seems to be at the very least a coherent sub personality, a coherent basin that you can push these models into.”

Current multi-agent systems lack durable and cumulative culture, unlike human social dynamics.

“There have been studies done with these multi-agent systems with like open claw. And oh, wow, looks like they are kind of approximating human interactions, but if you zoom in, there's nothing durable. There's no like cumulative culture.”

No scientific theory has ever been able to explain or computationally reproduce any specific conscious experience, such as the taste of mint.

“The hard fact is that to date there's not a single specific conscious experience that any scientific theory has ever been able to show we could program up.”