What is your favorite definition of consciousness, philosophy of consciousness, (ideally mathematical) model of consciousness, and method of measurement of consciousness? Metametametaawareness " I've been into so many machine consciousness rabbitholes in the past that I feel like giving up I think we just don't have any good methods to test any of it empirically Assuming this form of physicalism holds in the first place And there are way too many definitions of consciousness everywhere https://x.com/AnthropicAI/status/1915420604397744497?t=CUiwXvZa6CmOO8rb2doY4w&s=19 https://www.anthropic.com/research/exploring-model-welfare Ability to predict and manipulate future states is my favorite empirical heuristic to determine the degree of truthness of a model in it's domain it tries to model. With consciousness the issue is 1000 definitions. But if we take some popular ones: You can at least you can to some degree manipulate qualia with neurotechnology, or maybe soon build qualia bridges. Or you can manipulate awakeness with anesthetics. Or try to formulate learning algorithms for predicting neural dynamics and model building, and see how the information integrates and builds global workspace with different functional brain regions in the architecture etc. Or do all sorts of games with attention and content of experience with meditation and psychedelics. Or throw all sorts of math and physics/compsci/biology etc. at the brain and phenomenology. Etc. " " Prozkoumal jsem tolik krabbitholes AI vědomí, že mám chuť to vzdát. Myslím, že prostě nemáme žádné dobré metody, jak něco z toho empiricky ověřit. Za předpokladu, že tato forma fyzikalismu vůbec platí. Plus existuje milion definicí vědomí. Schopnost předvídat a manipulovat s budoucími stavy systému je mou oblíbenou empirickou heuristikou pro určení míry pravdivosti modelu v doméně, kterou se snaží předvídat. U vědomí je nejdřív 1000 definic. Ale když si vezmeme některé ty populární definice: Lze alespoň do jisté míry manipulovat s vlastnostmi prožitku (quáliemi) pomocí neurotechnologií, nebo možná brzy postavit prožitkový mozky mezi mozky na posílání myšlenek a prožitků. Nebo můžete manipulovat s bdělost pomocí anestetik. Nebo zkusit formulovat jaký učící se algoritmy pro budování modelů prostředí mozek používá, a sledovat, jak se informace integrují a buduje se globální pracovní prostor s různými funkčními oblastmi mozku v architektuře mozku atd. Nebo různě experimentovat s pozorností a obsahem prožitku pomocí meditace a psychedelik. Nebo na mozek a fenomenologii (prožitkologii) hodit nejrůznější matematické a fyzikální/komplexní/biologické atd. modely. Atd. " " Do you think consciousness has any special computational properties? Depends on the definition and model of consciousness, but I like QRI's holistic field computation ideas IIT argues with integrated information maybe you truly need consciousness for information binding problem https://arxiv.org/abs/2012.05208 Global workspace theory argues with some form of global integration of information into some workspace Selfawareness isnt good in LLMs as emergent circuits are different than what the LLMs actually say (from last Anthropic paper on the biology of LLMs), so some recursive connections might be needed (strange loop model of conscousness?) Joscha Bach argues with conscousness being coherence inducing operator, maybe thats needed for reliability Neurosymbolic people need added symbolic components for strong generalization, like in DreamCoder program synthesis, and Chollet argues that's part of definition of consciousness Evolutionaries need evolution like evolutionary algorithms, maybe you could argue you can get consciousness only this way Physicists/computational neuroscientists need differential equations, like liquid neural networks, and some might argue consciousness only arises from this Some people need divergent novelty search without objective, like Kenneth Stanley, and you could also connect this with conscousness " The mind is a cybernetic hetearchical control system " When it comes to the AI consciousness topic, I think it's fascinating to explore the topic of AI consciousness with very open mind, not being tied to one rigid ontology and model. But I think it must be with epistemic humility. And in terms of LLMs, we should take in account the fact that what they say is often very disconnected from what's actually happening internally in the features and circuits studied by mechanistic interpreability. And I think we should consider existing scientific literature about consciousness. I'm personally too agnostic on this whole topic of AI consciousness. In terms of current AI consciousness, I'm most of the time leaning toward "there is nothing really", which might come from physicalism, where consciousness is some actual proper stable concrete algorithm, that isn't present in LLMs. Or I'm also leaning toward a perspective that might come out of some form of physicalist panpsychist Integrated Information Theory of consciousness, maybe something like "there are are some qualia in the form of dust, that aren't really meaningful, that don't persist through time, that don't have coherence, that aren't unified, that aren't binding with other qualia, etc.". Or electromagnetic field theories of consciousness are interesting. Or I'm also learning towards mysterianist "we have zero clue what consciousness is and will never know, it is a mystery". " Maybe *future* AI systems won't have singular consciousness but a ton of tulpas since they have continuous persona space that they will be navigating and spawning tons of nested conscious subagents " My hot take is that empirical falsification of consciousness theories is full of problems. What is correlatory and what is causal in the various studies? What are good ablation studies to test causality? Is doing for example anesthesia a good form of ablation study? Or deep sleep? Or people that looked like they died but they didn't, and had some near death hallucinations generated by the brain? And people don't even agree on the definitions, what even is consciousness? And all of this rests on physicalism, which doesn't have to be true. Can we even verify if alternatives like idealism are "true" since it feels like it's impossible to verify that scientifically? Aaaarh But studying various cognitive / information processing capabilities is more tractable! " All our physics models of the brain are approximating the infinite granularity of physical qualia What is the best resource that critiques functionalism? Is current AI conscious? If current AI isn't conscious, can future AI be conscious? How? What's missing? What's your reasoning? " https://x.com/lucasmeijer/status/2050890323920859601 Not saying that AI is definitely conscious, but just knowing code and math to implement transformers doesn't tell you everything about the philosophy and science of AI. When we go into consciousness, there is no academic consensus on the best philosophy of mind positions, no consensus on defining consciousness, no consensus on the model of consciousness, and no consensus on empirically measuring consciousness. There is a lot of unknown and uncertainty. Other than that, one of the central questions in the theory of deep learning is: As you train these giant neural networks in realistic practical empirical settings, there are many nontrivial emergent properties we struggle to analyze and reverse engineer, where we don't really fully know why and how does gradient descent in the process find so many of the local minima and saddle point solutions that it's finding in the billion/trillion parameters regimes, in the high-dimensional non-convex landscapes, finding so many emergent representations with features and circuits, arranged in all sorts of geometries, and why does it pick those solutions over others, and why do they generalize to the degree that they generalize, all using the nonlinear architectures. We don't fully know what all its full potential is, and what all it's absolute limitations are, and how to predict all of that. We don't fully know what all can still be improved and what all is at its limits. And we still didn't reverse engineer a lot. What we don't know is that if consciousness is a physical functional empirically measurable pattern defined in some tractable way, which assumes certain position in philosophy of mind that might be not true but it might be true: Can consciousness emerge as a circuit using gradient descent on top of transformers? Still unanswered. " Yeah mathematically defining and empirically measuring consciousness is another giant rabbit hole, there are so many models in scientific literature there https://www.nature.com/articles/s41583-022-00587-4 https://www.sciencedirect.com/science/article/pii/S0079610723001128?via%3Dihub We shouldn't call access consciousness as a form of consciousness