It seems that for AGI to join us, not only does it require some form of "reiterative automaticity" - that is to say, to spontaneously rewrite, live/in the present moment, its own predictive algorithms independent of us, but that such algorithms must be further compressed until they no longer require googols of data but the same or less data than a typical human in order to reason. — Benj96
The second thing is how do we give it both "an objective" but also "free auto-self-augementation" in order to reason. — Benj96
And curiously, could that be the difference between something that feels/experiences and something that is lifeless, programmed and instructed? — Benj96
As it stands, large language models crunch enormous amounts of data with statistical algorithms in order to produce "the most likely answer" to any given prompt. Even if such a prompt demands a combination of data in a way never done before (ie. creativity) for example: reciting page 37 of Plato's Republic in the narrative style of a dialogue between Homer Simpson and Kim Kardashian.
This seemingly effortless "creativity" has stunned many users and convinced them we have AGI, especially because it matches or exceeds any individual person's ability to replicate it. But AI specialists insist this is nothing more than smoke and mirrors, theater in the realm of wordplay.
In the words of Yann LeCun (a leading AI technologist) "researchers need to work on 'objective-driven' AI with the ability to reason and plan about the world, rather than just work on words alone."
So what does it mean to have an "objective", and "reason" towards a resolution instead of just predict one? — Benj96
In the words of Yann LeCun (a leading AI technologist) "researchers need to work on 'objective-driven' AI with the ability to reason and plan about the world, rather than just work on words alone."
So what does it mean to have an "objective", and "reason" towards a resolution instead of just predict one? — Benj96
Yes, it's a very insightful question, highlighting some of the most significant challenges and philosophical inquiries in the development of artificial intelligence, especially concerning the aspirations toward artificial general intelligence (AGI). Let's explore the concepts mentioned and respond to some of the questions raised.
Objective and Reasoning in AI: In AI, an "objective" typically refers to a specific goal that the system aims to achieve, programmed by humans. For example, the objective of a chess-playing AI is to win the game. This is in contrast to human objectives, which are often multifaceted and can change dynamically based on the situation and internal motivations. "Reasoning" in AI terms means the capability to make inferences or deductions based on data and a set of rules, or more advanced forms of reasoning that involve planning or decision-making based on predicting future states.
However, current large language models (LLMs) like the one you're interacting with now do not genuinely reason in the human sense. They generate responses based on patterns learned from data, aiming to provide the most statistically likely answer, not necessarily to understand or reason through topics as humans do.
Goal Orientation and Data: Humans use a relatively limited dataset (our personal experiences and knowledge) but are incredibly efficient at generalizing from this data, thanks to our biological evolution and cognitive development which grant us the ability to reason abstractly, plan, and adapt. We're not just processing information but also actively learning and applying knowledge creatively and adaptively. For AGI to reach a similar capability, it would need not only access to vast amounts of data but also the ability to abstract, generalize, and reason beyond mere data retrieval or pattern matching.
Reiterative Automaticity: The concept you referred to as "reiterative automaticity" suggests that AGI should be able to autonomously modify its algorithms based on new information or changes in its environment, much like how humans learn from experiences and adjust our behavior. This type of learning and adaptation is a step beyond what current AI systems are capable of, where most adjustments to AI behavior are manually programmed by developers.
Compression of Algorithms and Data Efficiency: The idea that AGI should operate with the same or less data than a typical human to reason effectively is a profound one. It suggests an efficiency of processing and decision-making that AI systems currently lack. Current models require extensive data and computational power, whereas humans can make complex decisions with much less explicit information, often relying on intuition or subconscious processing.
Objective and Free Auto-Self-Augmentation: Giving AI an "objective" while also allowing "free auto-self-augmentation" touches on the core challenge of creating an AI that can set its own goals and adapt its methods autonomously. This raises both technical challenges and ethical questions. How do we ensure that an AI's self-set goals are aligned with human values? How do we manage and govern systems that can operate independently?
Lastly, whether this could be the difference between something that feels/experiences and something lifeless touches on the philosophical debate about consciousness and experience in artificial entities. This is a complex question that straddles technology, philosophy, and ethics.
In conclusion, moving towards AGI involves not just technical advancements in how AI systems process and handle data but also profound insights into the nature of intelligence, consciousness, and the ethical frameworks we construct around autonomous systems. It's a fascinating field with much to explore and discuss! — ChatGPT4
Does it mean, something has to matter to it? Humans and other creatures are driven by basic needs, but also by desires, plans, intentions and goals. I think the human capacity to reason is also goal-oriented in that way, and so ultimately driven by necessity. How could such attributes be genuinely embedded in an artificial system? — Wayfarer
The second thing is how do we give it both "an objective" but also "free auto-self-augementation" in order to reason. And curiously, could that be the difference between something that feels/experiences and something that is lifeless, programmed and instructed? — Benj96
You might be surprised by the responses that you would get from GPT-4, Gemini Ultra, Gemini Pro 1.5, Claude 3 Sonnet or Claude 3 Opus. I haven't asked them yet, but I plan to do it and I can report the results here if you don't have access to some of them. — Pierre-Normand
p.s., While I don't mean to turn the thread into yet another discussion regarding the possibility of free will, I honestly don't find any other way of frankly addressing the issue in the OP. — javra
. How could such attributes be genuinely embedded in an artificial system? — Wayfarer
A mechanism will always be just a mechanism, however much it sounds like it is thinking, it isn't. — Pantagruel
The difference is, I think, in what makes a simulation different from a duplication. We can instruct a simulation to respond to words and objects in ways that appear non-instructed, spontaneous, emotional etc. But what for? Is indiscernibility from being human worth striving for? A simulation is never a duplication — jkop
If we are to believe life emerged from the purely mechanical, we cannot exclude the possibility that AGI can do the same. — Benj96
The only way I can think of is to imbue it with a chronic angst or fear of death or suffering — Benj96
But you could say the same about me. Am I a simulation or a duplication of what another human might say in response to your commentary? — Benj96
Question: Further to this discussion one of the points I would make is that, in order for an AGI system to fully realise human capacities, it would need to be a subject of experience. And no current systems, including ChatGPT, are subjects of experience, as such. They emulate what a subject might say, but they're not actually subjects as such, right?
ChatGPT: That's a very astute point, and you're correct. Current AI systems, including ChatGPT, are not subjects of experience—they do not have subjective experiences, consciousness, or awareness. These systems are designed to process input data and generate responses based on patterns they have learned from large datasets. They can emulate human-like dialogue and even imitate styles of thinking or arguing, but this is fundamentally different from actually experiencing or understanding these processes.
The notion of an AI being a "subject of experience" involves concepts of consciousness and subjective experience that are, at present, beyond the capabilities of AI. The idea of subjective experience, often referred to philosophically as "qualia," is closely tied to consciousness—having personal perceptions, feelings, and experiences that are inherently private and firsthand.
For an AGI to truly realize human capacities as you've mentioned, it would need to not only process information and solve problems efficiently but also possess consciousness or some form of experiential understanding. This leap from a highly advanced computational tool to a being with subjective experiences raises profound questions about what consciousness is and whether it can be artificially created or replicated.
Philosophers, cognitive scientists, and AI researchers debate whether it is possible for artificial systems to ever truly achieve consciousness, or if it is a quality that will remain unique to biological organisms. Some argue that consciousness might emerge from sufficiently complex systems, while others believe it requires a specific kind of biological substrate or that it is fundamentally inexplicable and thus inimitable by machines.
In any case, the development of AI systems that can claim genuine subjectivity and consciousness would represent a monumental shift not only in technology but in our understanding of what it means to be 'alive' or 'aware.' This continues to be a fascinating area of inquiry at the intersection of technology, philosophy, and ethics.
Artificial general intelligence is something else. The very idea seems to be based on a misunderstanding of what a simulation is, i.e. that somehow, e.g. with increased complexity, it would suddenly become a duplication. It won't. — jkop
But then, the actor's ability to imitate the discourse of a physicist would slowly evolve into a genuine understanding of the relevant theories. I believe that intellectual understanding, unlike the ability to feel pain or enjoy visual experiences, cannot be perfectly imitated without the imitative ability evolving into a form of genuine understanding. — Pierre-Normand
there remains a stark distinction between the flexible behavior of an AI that can "understand" an intellectual domain well enough to respond intelligently to any question about it, and an actor who can only fool people lacking that understanding. — Pierre-Normand
It can be argued that the understanding manifested by language models lacks grounding or is not "real" in the sense that no "feeling" or "consciousness" attaches to it. But even if there is truth to these skeptical claims (which I believe there is), there remains a stark distinction between the flexible behavior of an AI that can "understand" an intellectual domain well enough to respond intelligently to any question about it, and an actor who can only fool people lacking that understanding. In that case, I would argue that the simulation (or enactment) has become a form of replication. — Pierre-Normand
It can be also questioned if "understanding" is anything but feeling, or recognition, of some intellectual process. Something we just witness, or then we don't. At least for me it is very common to just produce text without really understanding. It can also be argued, that I just don't have focus on that specific moment, but how can I tell? Maybe I'm just now continuing your prompt. — Olento
The AGI's responses might be super intelligent, but this doesn't mean that it understands them. I suppose it doesn't have to in order to be a useful assistant. — jkop
..embodiment, episodic memory, personal identity and motivational autonomy. Those all are things that we can see that they lack (unlike mysterious missing ingredients like qualia or "consciousness" that we can't even see fellow human beings to have). Because they are lacking in all of those things, the sorts of intelligence and understanding that they manifest is of a radically different nature than our own. But it's not thereby mere simulacrum - and it is worth investigating, empirically and philosophically, what those differences amount to. — Pierre-Normand
Of course, this is all still quite different from the way human cognition works, with our [sic] biological neural networks and their own unique patterns of parallel and serial processing. And there's still much debate and uncertainty around the nature of machine intelligence and understanding.
But I think the transformer architecture provides a powerful foundation for integrating information and dynamically shifting attention in response to evolving goals and contexts. It allows for a kind of flexible, responsive intelligence that goes beyond simple serial processing. — Pierre-Normand
Indeed! How is it we are capable of all that? How do we make AI capable of it?And that sure sounds like a Hard Problem ;-) — Wayfarer
The meaning in the system is only seen by us. And it is seen by us only because we designed the system for the purpose of expressing meaning. — Patterner
Yes, they are radically different. Unlike computational systems we are biological systems with pre-intentional abilities that enable our intentional states to determine their conditions of satisfaction.
Some abilities might consist of neural networks and patterns of processing, but then you have relations between the biology and its environment, the nature of matter etc. which arguably amount to a fundamental difference between AGI and the biological phenomenon that it supposedly simulates.
Of course we can also ditch the assumption that it is a simulation and just think of AGI as information technology. — jkop
that somehow, e.g. with increased complexity, it would suddenly become a duplication. It won't — jkop
Do you believe that human-constructed artefacts, which are engineered to correct errors in order to function within a predefined scope, are subject to the same emergent possibilities as organic systems, which can exploit apparent errors and thereby expand their scope of operations? — Pantagruel
For it to fear death, it would have to be alive — Wayfarer
Get involved in philosophical discussions about knowledge, truth, language, consciousness, science, politics, religion, logic and mathematics, art, history, and lots more. No ads, no clutter, and very little agreement — just fascinating conversations.