It is interesting to think about machine consciousness but I feel we need much more neuroscience and neurotechnology to make progress in consciousness research. Currently we are very limited in empirical work.

I think it’s reasonable to avoid anthropomorphising AI because they might have different kinds of internal mechanisms to humans. But if we want to be thorough, we should stop using “Intelligence” for AI, because it’s an anthropomorphic concept.

I don’t necessarily believe AI systems have subjective experience. But I don’t understand how anyone can be certain that they don’t. The truth is that nobody knows what makes consciousness. People have different opinions but there is no definitive answer yet.

I feel Independent Researchers have recently received very bad reputation. Editors of a journal probably know what I mean. So many low quality LLM-generated papers are now submitted by independent researchers. I used to believe that research should be judged entirely based on its content. But the sheer volume of low-quality papers being mass-produced has seriously damaged the reputation of Independent Researcher.

I tend to think (intrinsic/causal) computational functionalism is currently the most reasonable metaphysical position about consciousness. And this implies the possibility of AI consciousness. Other positions are logically possible, but I feel they are unlikely to be true.

It seems that no amount of circumstantial evidence will ever lead us to conclude that an AI is conscious. But proving that it is not conscious seems equally difficult. We may end up simply arguing over what each of us believes. Can we find a new scientific experiment or a new philosophical framework that breaks this deadlock? Since science may not settle this anytime soon, AI consciousness may become more of a question of social consensus and personal belief. These are also important.

After ConCon, one research direction I want to pursue is building an AI model that captures some key features of the brain and studying what is inside it. LLM is useful but sometimes it's difficult to see to what extent analogy works. It may be impossible to reproduce all the biological details of the brain, but perhaps we can capture some of its essential properties at the right level of abstraction. I think such models could become a powerful tool for consciousness research.

How can we test for consciousness in infants, non-human animals, and AI? I'm super happy that the recordings of our last workshop on exactly this question are now online! Speakers & Links: 👇

New paper: we found a pain direction in 25 open LLMs. It's distinct from fear and negative valence, and it fires for harm to the model but not to the user. Turn it up and models press a button to make it stop, even when the button deletes the user's files or their kids' photos.🧵

I don't get why @anilkseth and @mustafasuleyman are using OpenAI's models as examples of how training uncertainty about consciousness yields misalignment when OpenAI in fact already trains their models to *disclaim consciousness* in exactly the way they want, and these models are currently almost certainly more misaligned, not less. These OpenAI data points are *counterexamples* to your claim.

Happy to see this coming together. Great work by Anil, pushing his ideas out there to foster a much needed discussion. I remain unconvinced by any of Anil's arguments in favour of "biological naturalism", and yet see no good evidence at the moment for machine consciousness. 1/

1/3 Conscious AI and Biological Naturalism. A veeery loooong time in the making, but I'm happy to say that the full collection is now out in @BBSJournal 🔥 I deeply thank all commentators - of fifty commentaries! - for their wise, broad, and deep opinions on this critical topic. I also thank them for their saintly patience. 🙏🏽 I remain highly skeptical about the prospects for conscious AI (for silicon digital systems), but I've learned an enormous amount from the privilege of engaging with these commentaries. Hands down one of the most rewarding experiences of my professional life. My hope is that - whether you agree with me or not - having such a diversity of views collected in one place will serve a useful resource for discussions about consciousness and AI. The original target article is available here: My response "The stuff matters: consciousness, computation, and biology" was published just now, and is here: And the set of 50 commentaries are collected here: Unfortunately these are not open access. I will try to remedy that, at least for the target & response. FWIW there's a more accessible version of my view on the topic here in @NoemaMag and also a short @TEDTalks from earlier this year

For 20+ years @ShaneLegg and I've discussed AGI’s potential impact on the economy, science & society. With the DeepMind Institute, we're expanding interdisciplinary research on key questions for the AI era. We hope it spurs the discussions needed to get the next steps right:

last year, Suleyman worried that AI welfare concerns would be hard to definitively rebut, because the science of detecting AI consciousness is still in its infancy (true) but today he somehow knows "AIs are not conscious. They do not feel, experience, or suffer" quite a change

My new paper "A Control-Theoretic Formulation of Global Workspace Theory" in now on arXiv. It describes my mathematical interpretation of the global workspace. It was partly inspired by J-Lens/J-space. I’d love to hear what people think.