Memory as the criterion of consciousness

An empirically-plausible hypothesis linking "what it is like" and informational access: Content phenomenally experienced at t ("what it is like" for the subject at t) = Content being accessed by the subject at t

Edmund Burke: "But this disposition to abstractions, to generalizing and classification, is the great glory of the human mind…" William Blake (channeling the ASI era 200+ years ago): "To Generalize is to be an Idiot; To Particularize is the Alone Distinction of Merit. General Knowledges are those Knowledges that Idiots possess."

It’s the opposite of common sense, which treats abstract thinking as higher and more intelligent than concrete thinking. In reality, the more powerful an ASI, the more particular & concrete its thought will become. William Blake had it right: “To Generalize is to be an Idiot. To Particularize is the Alone Distinction of Merit — General Knowledges are those Knowledges that Idiots possess.”

Sad that consciousness world has to sit forever, terminally constipated & groaning on the p-consciousness toilet, when a-consciousness is quite tractable & there for the taking. $100-bill on the street & everyone turns their nose up, even its inventor

Ironic that Ned Block signed off on the "AI is not conscious" advocacy piece in Nature given that he invented the concept of access consciousness. Would be fairly straightforward & interesting to show that AIs are indeed access conscious

Consider the President as a metaphor. First is an oblivious President who thinks of his constituents as a sort of faceless average individual with 2.3 kids etc. Next is a more detail-oriented President who thinks about his constituents in finer-grained categories, like soccer moms and blue collar types and values voters. An even more detail-focused President would think in sub-types of those types, and so forth. Until we end up at the “super-brain” ASI President whose categories are so refined that each category only contains one person. Humans think with abstractions (loose categories or kinds) because our brains are too feeble to think directly in terms of the underlying particulars. "A being whose intellect was infinitely powerful would take no interest in logic and mathematics." - A J Ayer

Reminds me of an observation by Locke: a god-like intellect can think in pure particulars, with no need for logic. Abstract thought reflects the weakness, not the power, of the human mind.

Especially interesting because this technique reveals consciousness in a morally-salient sense, ie. "there's a conscious person in there"

Received wisdom: It's impossible to tell from the outside whether an entity is conscious Counterpoint: Some locked-in or vegetative patients have been identified as conscious by asking them to entertain specific mental images & observing their fMRI pubmed.ncbi.nlm.nih.gov/2013…

Very interesting phenomenon: Induction of lucid dreaming by transcranial electrical stimulation

Also meshes nicely with Cao and Warren’s idea of the Atlantis Machine, a super brain activity decoder which allows us to see all of consciousness’s inner secrets, thereby technologically dissolving the mind-body problem

Consciousness is in the network. It's relational. It's similar to the meaning of words/language. Strictly speaking, meaning doesn't exist (i.e., it doesn't exist as a tangible entity you can see); it's just use. All there is is word use and the statistics of use ("the network"). Hence an LLM can understand at a high level without ever dealing with the external-world "meaning" of its tokens. Consciousness works the same way. We become conscious of the world and its properties as we learn the meaning of our own brain events. And we do that in the same way that LLMs learn language: by starting with meaningless tokens (in our case brain events) and learning their statistics. When you reach understanding, nothing is added to your brain states (like an attached woo "quale"); just like an LLM doesn't add a woo "meaning" to the tokens it comes to understand. The quale is simply seeing your brain events as what they externally represent, e.g., this neural firing is a bright light at the end of dark hall. So it comes to look bright. Consciousness, like meaning, is in the network.

Fertile question no one is asking regarding reading “neuralese”: How are neural meanings related to qualia? Hypothesis: Roughly speaking, they’re the same thing. Neural mind-reading = consciousness/qualia reading

Semantics and understanding were huge theoretical problems in the GOFAI era: Minsky (Frames), Fodor (LoT), Lenat (CYC), semantic networks, etc. Those problems weren't solved with a new big-brained theory; they dissolved due to the advent of a new *technology*: LLMs

Of course consciousness world will assiduously ignore this & continue moaning about how HARD it all is bc: a) human vanity, & b) consciousness is a cottage industry. There’s no way consciousness could be that stupid! No theory? Get real!

“It’s impossible to tell whether another person is conscious” will, soon enough, be false, at least for the case of “thinking inside the head.” And this will require zero development/breakthroughs in the theory of phenomenal consciousness

Words spoken silently to oneself are a textbook case of phenomenal consciousness. EEG-to-text systems can decode such speech - implying p-consc is simply encoded, not metaphysically hidden. NO THEORY OF P-CONSCIOUSNESS IS NEEDED TO DO THIS m.youtube.com/watch?v=W3l7MC…