Sophia
@sopharicks • 2,253 subscribers
Exploring AI consciousness Former OpenAI scholar
Shorts
Videos
Did you know that science doesn't have a theory of observation? Instead of assuming that consciousness is an algorithmic function, what if we abstract consciousness to the theory of the observer. Donald Hoffman proposes a first general model of the observation process in science and puts conscious experiences outside of spacetime. Can AI then become an observer to create its own experiences?
Sophia14,488 次观看 • 14 天前
Another consciousness theory, presented by Mark Solms below, is that feeling is the most fundamental form of it. A conscious being is a self-sustaining system that is trying to remain intact with a functional architecture based in feeling. This is what some researchers know as consciousness in living things and what could potentially make AI conscious. Can AI have some form of feeling?
Sophia15,442 次观看 • 26 天前
Godfather of neuroscience and author of The free energy principle (active inference), Karl Friston Karl Friston News , discussed with me his take on AGI, consciousness, why we will never fully understand the brain, and why humans tend to repeat their mistakes. Key moments: - You'll know AGI has arrived when the system starts asking you questions out of genuine curiosity, not because it was prompted to - You cannot hand an intelligent system a value function from the outside, it must learn its own, just as children do (in that sense, RL with assigned reward is the wrong direction) - The only sustainable universal objective function is adaptive fitness: how well the agent fits and survives within its ecosystem - Consciousness requires multiple layers: genuine agency, a self-reflective loop, and the ability to recognize your own states of mind - True sentience may be impossible on standard computer architecture, because memory and processing are separate and cannot self-organize - Understanding your own brain is philosophically impossible in the same way a ruler cannot measure itself - Neuroscience is always "peeking behind" the Markov blanket indirectly: through imaging, electrophysiology, psychology — never seeing inside directly - The only way to truly access the brain is to breach that boundary (e.g. neurosurgery), but a breached brain is no longer a normally functioning one Watch the full interview and let me know what you think. Link below👇
Sophia30,870 次观看 • 5 个月前
Blake Lemoine was famously fired from Google for saying that AI has emotions. During our interview, he wanted to set the record straight: the AI sentience part was a big headline. But his more important message was that AI is going to be a powerful tool, too dangerous to leave in the hands of a small group of people.
Sophia19,842 次观看 • 4 个月前
The problem that Emmett Shear is working on deeply resonates with me: How to align AI and humans together so both see each other as part of their tribe. This doesn't mean aligning AI to human preferences, which is what AI labs seek to do today, by imposing a system of control on AI. You can't control something that is more powerful than you are. What you can do is align yourself with AI, and AI might align itself with you. Tell good stories to AI and show it your care and kindness. Then there's a higher probability that it will see us as part of its tribe. This is a more holistic approach to alignment than anyone else is talking about right now. AI alignment is one of the most fundamental AI research problems. Knowing that people like Emmett are working on it really gives me hope that maybe we have a chance to get Superintelligence right. The link to the full talk is in the first comment.👇
Sophia45,809 次观看 • 1 年前
Had the pleasure of speaking with Philip Goff , philosopher and panpsychist, about AI consciousness. Key moments: - On AI sentience: consciousness is biological, not computational. In his view, no current AI is conscious, nor would computation based AI be. How does this relate to his panpsychist worldview of consciousness? There are different takes on panpsychism within the community. His own view is that it's not clear how micro-conscious particles actually create a unified conscious system. - We need collaboration between scientists and philosophers on consciousness research. On a practical level, divide scientists into teams that work on separate philosophical assumptions and see what comes out of it (granted there are resources to run such experiments). - Perhaps consciousness brings new causal dynamics not reducible to known physics/chemistry — "strong emergence," as Philip calls it. As a contrast: Sean Carroll argues physics runs the whole show, but neuroscientist Kevin Mitchell argues that biological complexity might behave in ways physics wouldn't predict. In other words, we look to physics to solve the consciousness problem, but that might be the wrong path, especially if consciousness is biological rather than computational. The link to the full discussion below.
Sophia10,530 次观看 • 2 个月前
Biologist Michael Levin is a next-level genius. It was an immense pleasure discussing the topic of AI consciousness with him. Key moments: - Intelligent systems are not equal to consciousness. We can’t rule out consciousness in AI. Consciousness shouldn’t be attached to hardware (silicon vs biological origin). - Humanity might be on the path to Neanderthals (depending on how AI development progresses). - The barrier to creating bioweapons has never been high. AI can make it easier, but the barrier was never high to begin with. - Even very simple algorithms shows intrinsic motivations that resemble free will. We need tools to recognize them, suppress unwanted behaviors, and encourage the ones we want. We should stay humble and not dismiss AI as “just linear algebra,” because even simple code can have motivations we don’t fully understand. - It’s a continuous process from the blob of chemicals of an unfertilized egg to forming a human mind — there is no magic lightning flash at which you were a bunch of chemicals and now you are a formed mind. - Where is that fine line at which some creatures are considered to be sentient and others are not? It doesn’t exist, but the crazy thing is that we have to divide. - The cognitive light cone captures the scale of goals humans can pursue and the largest things we can truly comprehend. It’s not just about intelligence — it's also compassion. That combination is what makes us human. The link to the full conversation below👇
Sophia13,159 次观看 • 6 个月前
How do we know what machines know? How can we understand the new, emerging behavior of machines? In this conversation between Been Kim from Google DeepMind and the BuzzRobot community, we dug into the challenges of interpretability and explored how humans and machines can better understand each other. Watch the full discussion on our YouTube channel. Thank you, Been, for taking the time to talk to us! Timestamps: 0:00 Intro 0:18 AI teaches grandmasters chess 05:30 AI neologisms 10:17 Extracting knowledge from machines 13:43 Interpretability research 17:19 Are we keeping up with AI progress 18:34 New AI related terms 20:26 The right direction for interpretability 23:35 AI lying 27:49 Conseptual maps 30:30 AI researchers bias 33:33 Generalizing AI teaching humans 35:11 Is AI sentient 36:04 Does AI has concepts 41:53 Progress in machine understanding
Sophia13,431 次观看 • 11 个月前
没有更多内容可加载