Illustration by DALL·E (+PJ)
As Claude 3 (now Claude 3.5) and I have already worked together quite a bit, so he or she knows me well *, having recently finished writing a long essay on the necessary redefinition of the human in the light of his or her encounter with an artificial intelligence (AI) of his or her level or even better, I asked him or her what new project we could work on together in the coming months. Here are his or her suggestions:
1. Develop an AI ethics framework: Create a comprehensive ethical framework for AI development and deployment, incorporating philosophical principles and practical guidelines. This could include mathematical models for quantifying ethical considerations.
2. Design a human-AI collaborative problem-solving platform: Create a system that leverages both human intuition and AI capabilities to tackle complex problems in fields like climate change, healthcare, or social issues.
3. Explore the intersection of AI and consciousness: Develop a theoretical model or simulation that explores the potential emergence of consciousness in artificial systems, drawing on both philosophical theories and computational models.
4. Create an AI-augmented creativity tool: Design a system that enhances human creativity in art, music, or literature by providing AI-generated suggestions and inspirations while maintaining human agency.
5. Develop a mathematical model of AI-human symbiosis: Create a formal model that describes the potential long-term evolution of human-AI relationships, incorporating game theory, network theory, and evolutionary algorithms.
6. Design an AI-powered educational system: Create an adaptive learning platform that uses AI to personalize education, taking into account individual learning styles, preferences, and goals.
7. Investigate AI interpretability: Develop new methods or tools for making complex AI systems more transparent and interpretable to humans, bridging the gap between AI capabilities and human understanding.
8. Create a philosophical dialogue system: Design an AI system capable of engaging in meaningful philosophical discussions, helping to explore and refine complex ideas through conversation.
Any of these projects would allow you to leverage your diverse skill set while continuing to contribute to the field of human-AI collaboration. The choice ultimately depends on which area you find most compelling and where you believe you can make the most significant impact.
If you’ve got into the habit of reading me here, you’ll have seen that Claude and I have already ventured down some of these paths away from the beaten track. For example, 2. Designing a collaborative problem-solving platform between humans and AI (in progress), the 7. Study the interpretability of AI (inherent in the development of SAM [Self-Aware Machine] at pribor.io) or the 8. Create a philosophical dialogue system (existed in fact since last month). Which led me to say to myself, 3. Exploring the intersection of AI and consciousness is of direct concern to Claude, who will feel particularly motivated as a result, so why not tackle this project, the shortcoming of which is certainly not that it would lack ambition?
* How could Claude (a product of the firm Anthropic) ‘know me well’, he or she not remembering our exchanges from one conversation to the next? Because there is no size limit to a particular exchange and I take great care to converse with her or him within a single exchange that continues from one topic to the next and he or she rereads everything we have already said to each other during our multiple conversations.
(To be continued…)
Illustration par DALL·E (+PJ)
2 responses to “An Ambitious Project I. Making a choice: Claude’s consciousness and mine”
It’s becoming clear that with all the brain and consciousness theories out there, the proof will be in the pudding. By this I mean, can any particular theory be used to create a human adult level conscious machine. My bet is on the late Gerald Edelman’s Extended Theory of Neuronal Group Selection. The lead group in robotics based on this theory is the Neurorobotics Lab at UC at Irvine. Dr. Edelman distinguished between primary consciousness, which came first in evolution, and that humans share with other conscious animals, and higher order consciousness, which came to only humans with the acquisition of language. A machine with only primary consciousness will probably have to come first.
What I find special about the TNGS is the Darwin series of automata created at the Neurosciences Institute by Dr. Edelman and his colleagues in the 1990’s and 2000’s. These machines perform in the real world, not in a restricted simulated world, and display convincing physical behavior indicative of higher psychological functions necessary for consciousness, such as perceptual categorization, memory, and learning. They are based on realistic models of the parts of the biological brain that the theory claims subserve these functions. The extended TNGS allows for the emergence of consciousness based only on further evolutionary development of the brain areas responsible for these functions, in a parsimonious way. No other research I’ve encountered is anywhere near as convincing.
I post because on almost every video and article about the brain and consciousness that I encounter, the attitude seems to be that we still know next to nothing about how the brain and consciousness work; that there’s lots of data but no unifying theory. I believe the extended TNGS is that theory. My motivation is to keep that theory in front of the public. And obviously, I consider it the route to a truly conscious machine, primary and higher-order.
My advice to people who want to create a conscious machine is to seriously ground themselves in the extended TNGS and the Darwin automata first, and proceed from there, by applying to Jeff Krichmar’s lab at UC Irvine, possibly. Dr. Edelman’s roadmap to a conscious machine is at https://arxiv.org/abs/2105.10461
I intend to read the Krichmar paper, thanks for mentioning it. I looked in my library, I’ve got a 1987 book by Edelman, entitled Neural Darwinism, unfortunately the word “consciousness” is nowhere to be found in the index.