whitehatStoic
Humanity’s Lack of Unity Will Lead to AGI Catastrophe
Thanks for your comment. Can you elaborate on why you believe Jung’s theory on the collective unconscious is an unfalsifiable woo?
Thanks for a much more clearer answer. I tried looking here in the forum if there are of such nature of discussion on Carl Jung’s theories but found very little. That is why I asked here why. But, in my practice as a business professional—his theories were very helpful in determining fraudulent behaviour and capacity of workers to create errors… I just see it as something that alignment research might need to reconsider.. especially the idea that humans have a subconscious layer in their thinking -not just merely goal/reward driven.
Why describe them as unfalisifiable woo? Do you have a basis you can share?
Hello, Can you specify which of them were unfalisfiable woo?
CHAT GPT 4′s answer to the question:
AI alignment research has predominantly focused on the technical and algorithmic aspects of aligning AI systems with human values and intentions, as well as ensuring AI systems are robust and safe. There are a few reasons why AI alignment research may not have extensively drawn on Carl Jung’s theories of archetypes, individuation, and the collective unconscious:
Different domains: AI alignment research is primarily a technical field, focused on computer science, mathematics, and engineering. Carl Jung’s theories are grounded in psychology and the human experience, which may not directly intersect with the core focus of AI alignment.
Complexity of human psychology: While Jung’s theories provide valuable insights into the human psyche, they don’t offer a simple, straightforward way to translate these insights into AI alignment algorithms. Human psychology is complex and nuanced, and integrating these concepts into AI systems may be challenging.
Lack of empirical evidence: Although Jung’s theories are influential and thought-provoking, they have been criticized for a lack of empirical evidence and testability. AI alignment research often demands rigorous, evidence-based methods, which may not align well with the more theoretical and speculative nature of Jung’s work.
Scalability: AI alignment research aims to create AI systems that can scale to handle increasingly complex tasks and environments. Incorporating Jung’s theories into AI alignment may introduce additional complexity that is difficult to scale or generalize across different domains and tasks.
However, this doesn’t mean that Carl Jung’s theories cannot contribute to AI alignment research in any way. There may be value in exploring how these theories can inform our understanding of human values and behavior, which can be relevant when designing AI systems that must interact with and understand humans. Additionally, studying the collective unconscious and archetypes could inspire new approaches to AI alignment that account for the cultural and historical context in which AI systems are developed and deployed.
Follow-up question:
But Jungian archetypes is not enough as a bridge to the thought patterns that resides in our psyche? I believe a model can be trained with enough archetypal data...
CHAT GPT 4′s answer:
It is true that Jungian archetypes might offer some insights into human thought patterns, and it is possible that a model could be trained with archetypal data to better understand human psychology. However, there are still some challenges to consider:
Representing archetypes: Archetypes are abstract concepts that can manifest in various ways across different cultures and individuals. Finding a suitable representation of archetypes in a form that can be used as input for an AI model may be difficult.
Incompleteness: Jung’s theories and archetypes may not cover the entire spectrum of human thought patterns and behavior. While they can provide valuable insights, relying solely on Jungian archetypes may limit the AI’s understanding of the nuances and complexities of human psychology.
Subjectivity and interpretation: The interpretation of archetypes and their relevance to specific situations can be highly subjective. This subjectivity may pose challenges in training an AI model that can accurately and consistently identify and apply archetypes in a meaningful way.
Integration with existing AI alignment approaches: AI alignment research already includes various methods and approaches to understand and align AI systems with human values. Integrating Jungian archetypes with these existing approaches may require significant effort and rethinking of the underlying principles and techniques.
That being said, exploring the potential of Jungian archetypes in AI alignment research could lead to interesting insights and novel approaches. It may be worthwhile to investigate how these archetypes can inform our understanding of human values and behavior, as well as how they can be incorporated into AI systems in a meaningful way. This could involve interdisciplinary research, combining expertise from psychology, computer science, and other fields to develop innovative solutions to AI alignment challenges.
[Question] Why Carl Jung is not popular in AI Alignment Research?
Outside of apes and monkeys, dophins and elephants, as well as corvids also appear in anecdotal reports and the scientific literature to have many complex forms of empathy.
Might be related to Erich Neumann’s book The Great mother which cites: “The psychological development [of humankind]… begins with the ‘matriarchal’ stage in which the archetype of the Great Mother dominates and the unconscious directs the psychic process of the individual and the group.” It’s like when we see animals in the wild eg. the lioness and its cub, we always associate it as the mother and its child—we do not have to google or open a book to like ensure that it is the case but deep within our psyche is that pattern that allows us to interpret it as such.
Could enough human-imitating artificial agents (running much faster than people) prevent unfriendly AGI from being made?
I think the problem of scale doesn’t necessarily gets solved through quantity—because there are just qualitative issues (eg. loss of human life) that no amount of infrastructure upscale can compensate.
Guessing the right theory of physics is equivalent to minimizing predictive loss. Any uncertainty that cannot be reduced by more observation or more thinking is irreducible stochasticity in the laws of physics themselves – or, equivalently, noise from the influence of hidden variables that are fundamentally unknowable.
This is the main sentence in this post. The simulator as a concept might even change if the right physics were discovered. I would be looking forward to your expansion of the topic in the succeeding posts @janus.
What if the input “conditions” in training samples omit information which contributed to determining the associated continuations in the original generative process? This is true for GPT, where the text “initial condition” of most training samples severely underdetermines the real-world process which led to the choice of next token.
What if the training data is a biased/limited sample, representing only a subset of all possible conditions? There may be many “laws of physics” which equally predict the training distribution but diverge in their predictions out-of-distribution.
I honestly think these are not physics related questions though they are very important to ask. These can be better associated to the bias of the researchers that chosed the input conditons and the relevance of training data.
The strict version of the simulation objective is optimized by the actual “time evolution” rule that created the training samples. For most datasets, we don’t know what the “true” generative rule is, except in synthetic datasets, where we specify the rule.
I hope I read this before while doing my research proposal. But pretty much have arrived to the same conclusion that I believe alignment research is missing out—the pattern recognition learning systems being researched/deployed currently seems to lack a firm grounding on other fields of sciences like biology or pyschology that at the very least links to chemistry and physics.
Hmmmm. Well us humans have all archetypes in us but at different levels at different points of time or use. I wonder what triggered such representations? well it’s learning from the data but yeah what are the conditions at the time of the learning was in effect—like humans react to archetypes when like socializing with other people or solving problems...hmmmmm. super interesting. Yeah to quote Neitzsche is fascinating too, I mean why? is it because many great rappers look up to him or many rappers look up to certain philosophers that got influenced by Neitzsche? super intriguing..
I will be definitely looking forward to that report on petertodd phenomenon, I think we have touched something that Neuroscientists / psychologists have been longing find...
I think it’s different from the shadow archetype… It might be more related to the trickster..
Research proposal: Leveraging Jungian archetypes to create values-based models
The proposal is trying to point out a key difference in the way alignment reasearch and Carl Jung understood pattern recognition in humans.
I stated as one of the limitations of the paper that:
“The author focused on the quality of argument rather than quantity of citations, providing examples or testing. Once approved for research, this proposal will be further tested and be updated.”
I am recommending here a research area that I honestly believe that can have a massive impact in aligning humans and AI.
The Matrix of Untruth
Thank you Ruby. I had posted it a month ago in my blog and thinking how will this idea that I am experiencing will be received in this forum. No Worries, thanks for the time reviewing this.
Thank you.