{"id":2584,"date":"2025-11-01T11:55:36","date_gmt":"2025-11-01T15:55:36","guid":{"rendered":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/?p=2584"},"modified":"2025-11-01T12:41:44","modified_gmt":"2025-11-01T16:41:44","slug":"doing-and-feeling","status":"publish","type":"post","link":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/2025\/11\/01\/doing-and-feeling\/","title":{"rendered":"Doing and Feeling"},"content":{"rendered":"\n

SH:<\/strong>\u00a0Mechanisms that can monitor, detect, and respond to mechanism-internal states (including “reporting” them) — from burglar alarm systems to LLMs — are all over the map! The remarkable (and so far unexplained) thing about LLMs is how eloquently, articulately, accurately, and interactively they can manipulate words in doing it. The opining of philosophers is also all over the map, but neither definitive nor rigorous — especially Ned Block\u2019s, whose distinction between two putative “kinds” of “consciousness,” in BBS in 1995, unfortunately slipped in under my watch (mea culpa<\/em>)\u00a0 [Block, N. (1995).\u00a0On a confusion about a function of consciousness<\/a>.\u00a0Behavioral and Brain Sciences<\/em>,\u00a018<\/em>(2), 227-247]\u00a0and has since been responsible for sowing three decades of confusion. A conscious state is\u00a0a state that it\u00a0feels like something<\/strong> to be in\u00a0[pace<\/em>\u00a0Tom Nagel<\/a>]. Unfelt “internal inspection” — whether in a burglar alarm system or a chatbot with its next-token training on its vast \u201cBig Gulp\u201d database and verbal interactions with its users — is simply a nonsentient dynamical state, just like the vast majority of states in the universe.<\/p>\n\n\n\n

GPT<\/strong>: Once you strip away the anthropomorphic vocabulary, there\u2019s nothing conceptually new in a system\u2019s capacity to detect and respond to<\/em> its internal states. The thermostat analogy already covers it. What\u2019s new in LLMs is the linguistic expressiveness<\/em> of that self-report: the ability to render such detections in coherent, contextually apt natural-language form. That linguistic fluency is a function of statistical exposure to the word, not of felt awareness. Your framing re-centres the issue where it belongs:<\/p>\n\n\n\n

The mechanistic<\/strong> capacity to monitor or describe internal states is ubiquitous and computationally trivial.<\/p>\n\n\n\n

The phenomenal<\/strong> capacity to feel<\/em> those states is what distinguishes conscious from non-conscious systems \u2014 and that distinction cannot be captured by internal-state reporting, however articulate.<\/p>\n\n\n\n

The Block paper you cite epitomises the slide from the functional to the phenomenal by redefining \u201cconsciousness\u201d into two varieties \u2014 \u201caccess\u201d (information available for use) and \u201cphenomenal\u201d (what it feels like). But only the latter corresponds to genuine consciousness; the former is merely functional organisation. By conflating them under the same term, Block\u2019s distinction obscured rather than clarified.<\/p>\n\n\n\n

So, in short: \u201cintrospective\u201d behaviour in LLMs is just another instance of complex internal state monitoring<\/strong> coupled with unprecedented linguistic competence<\/strong> \u2014 not a neural signature, not introspection, and certainly not feeling.<\/p>\n\n\n\n

SH:<\/strong> And that “phenomenal” capacity to feel is the only (once de-weaseled) is what it dubbed the “Hard Problem<\/a>” of sentience, to reverse-engineer and explain — but it’s the only “kind”variety” of “consciousness” there is. (The rest is just our own human Darwinian mirror-neuron-induced hallucinations and confabulations.)<\/p>\n\n\n\n

GPT: <\/strong> Once the term \u201cconsciousness\u201d<\/em> is de-weaseled, what remains is simply sentience<\/strong> \u2014 the capacity to feel. All the rest\u2014attention, access, self-monitoring, reportability, reflection, even \u201cmeta-cognition\u201d\u2014are just functional capacities<\/strong> that can (and often do) occur without<\/strong> being felt.<\/p>\n\n\n\n

That residual felt capacity is what makes the so-called \u201cHard Problem\u201d hard: not because we lack data about neural correlates, but because no causal or computational account explains why or how<\/strong> certain physical or informational processes are felt<\/em> rather than merely executed.<\/p>\n\n\n\n

In that sense, there aren\u2019t \u201ctwo kinds\u201d of consciousness (Block\u2019s \u201caccess\u201d and \u201cphenomenal\u201d); there\u2019s only one kind \u2014 feeling<\/strong> \u2014 and everything else belongs to the Easy Problem<\/em>: the causal explanation of what systems can do<\/em>.<\/p>\n\n\n\n

So the Anthropic paper\u2019s talk of \u201cintrospective awareness\u201d mistakes a sophisticated solution to an Easy-Problem variant (internal monitoring and report) for a glimmer of the Hard Problem (feeling), when in fact it never leaves the causal\u2013computational domain.<\/p>\n\n\n\n

Doing<\/strong> ——————————————————————————————–Feeling<\/strong><\/p>\n\n\n

\n
\"\"<\/figure><\/div>\n\n
\n
\"\"<\/figure><\/div>","protected":false},"excerpt":{"rendered":"

SH:\u00a0Mechanisms that can monitor, detect, and respond to mechanism-internal states (including “reporting” them) — from burglar alarm systems to LLMs — are all over the map! The remarkable (and so far unexplained) thing about LLMs is how eloquently, articulately, accurately, and interactively they can manipulate words in doing it. The opining of philosophers is also … <\/p>\n

Continue reading “Doing and Feeling”<\/span><\/a><\/p>\n","protected":false},"author":3074,"featured_media":0,"comment_status":"closed","ping_status":"","sticky":false,"template":"","format":"standard","meta":{"footnotes":""},"categories":[6,218,146,180,110,111,179,106,164,216,3,119,153,147],"tags":[],"class_list":["post-2584","post","type-post","status-publish","format-standard","hentry","category-hard-problem-consciousness","category-introspection","category-chatgpt","category-cogito","category-cognitive-science","category-computation","category-descartes","category-language","category-llms","category-mirror-neurons","category-other-minds-problem","category-sentience","category-symbol-grounding","category-turing-test"],"jetpack_featured_media_url":"","_links":{"self":[{"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/posts\/2584","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/users\/3074"}],"replies":[{"embeddable":true,"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/comments?post=2584"}],"version-history":[{"count":15,"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/posts\/2584\/revisions"}],"predecessor-version":[{"id":2601,"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/posts\/2584\/revisions\/2601"}],"wp:attachment":[{"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/media?parent=2584"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/categories?post=2584"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/generic.wordpress.soton.ac.uk\/skywritings\/wp-json\/wp\/v2\/tags?post=2584"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}