Connectionists: Fwd: Statistics versus “Understanding” in Generative AI.

[Keith Lambert]

Gary, enough with the language games and goal post shifting…is this a
bijective map from biological to technological cognition and understanding?
No, but is there a one to one mapping from birds to planes? No…but do both
fly? Yes…simple analogy but think it proves my point…stop looking for this
one to one correlate and univariate explanation for intelligence,
understanding, etc…it’s definitely doing something, but the lack of
appropriate linguistic representation for the phenomena shouldn’t
disqualify the existence of it…do we need new ‘notation’ to describe and
understand (pun intended) this new technological information processing
system, yes, but does this deny what is happening here because we lack that
linguistic clarity, no. How’s about stepping off the anthropocentric train
for a minute and think of this objectively as an advanced technological
entity the likes of which we’ve never seen before and thus struggle with
the categorization of it? Just a ‘thought’….whatever that means🤔😉🤷🏼‍♂️
P.S.
Also, thinking about Frege’s linguistic turn here, and that we’re talking
the same ‘sense’ here but a different ‘referent’ as well as the
understanding of numbers as parts of a logical system and not objects in
and of themselves. I think healthy and spirited dialogue are great. Too
much negativity and vitriol around this IMHO

Best,
Keith

Sent from my iPhone


On Fri, Feb 16, 2024 at 9:54 AM Gary Marcus <gary.marcus at nyu.edu> wrote:

> Always with the childish ad hominem.
>
> This field is something else.
>
> On Feb 15, 2024, at 11:09 PM, Terry Sejnowski <terry at snl.salk.edu> wrote:
>
>  GPT-4 is a moving target that may eventually replace Gary.
>
> Terry
>
> -------
>
>
>
> The request you've made is similar to one I've already fulfilled. The
> image generated earlier depicts an empty room without any elephant present,
> adhering to your specific instructions. If you need any further adjustments
> or have another request, feel free to let me know!
>
> ------
> [image: User]
>
> Write a critique of ChatGPT in the style of Gary Marcus
>
> ChatGPT
>
> Writing a critique of ChatGPT in the style of Gary Marcus, a scientist
> known for his clear-eyed scrutiny of artificial intelligence's capabilities
> and limitations, presents an intriguing challenge. Marcus, with his deep
> understanding of both the potential and pitfalls of AI, often emphasizes
> the importance of grounding AI advancements in robust, generalized learning
> principles, rather than overreliance on data and statistical patterns.
>
> *Critique of ChatGPT in the Style of Gary Marcus:*
>
> ChatGPT, while a marvel of contemporary AI technology, epitomizes the
> quintessential limitations that besiege deep learning models. At its core,
> ChatGPT is a linguistic colossus, built upon the edifice of the transformer
> architecture, yet it is fundamentally constrained by the inherent
> limitations of its training methodology and underlying principles. The
> brilliance of generating coherent, contextually appropriate responses is
> overshadowed by its occasional lapses into confabulation, a glaring
> testament to its lack of true understanding.
>
> Gary Marcus would likely point out that ChatGPT, for all its linguistic
> dexterity, lacks the nuanced grasp of the world that humans possess. It can
> mimic the form of human knowledge and discourse, but it doesn't truly
> comprehend the content in the way a human does. This distinction is
> crucial; it is the boundary between a sophisticated parrot and an entity
> capable of genuine thought and understanding. ChatGPT's responses, no
> matter how convincing, are ultimately derived from patterns in data it has
> been fed, not from an intrinsic understanding of those patterns.
>
> Furthermore, Marcus might criticize ChatGPT's reliance on sheer volume of
> data as a substitute for a more nuanced, rule-based understanding of
> language and the world. This data-driven approach can lead to impressive
> performances in many scenarios but falls short when faced with novel
> situations or when required to apply common sense reasoning that hasn't
> been explicitly encoded in its training data. The model's occasional
> incoherence or its propensity to generate plausible but factually incorrect
> responses are symptomatic of this deeper issue.
>
> Another point of critique would likely focus on the opacity of ChatGPT's
> decision-making process. Despite recent advances in making AI models more
> interpretable, understanding how ChatGPT arrives at a particular response
> remains a challenge. This opacity complicates efforts to debug or improve
> the model, especially when it produces erroneous or nonsensical outputs.
> For AI to truly advance, Marcus might argue, it must not only perform well
> but do so in a manner that is transparent and understandable to human
> overseers.
>
> In the spirit of Marcus's advocacy for a hybrid approach to AI
> development, one could argue that integrating ChatGPT's statistical prowess
> with more structured, rule-based systems could ameliorate some of its
> shortcomings. By grounding the model's responses in a framework of logical
> reasoning and factual correctness, one might achieve a more reliable,
> genuinely intelligent system that better approximates human cognition.
>
> In conclusion, while ChatGPT represents a significant achievement in
> natural language processing, its limitations underscore the need for a more
> comprehensive approach to AI. An approach that incorporates the strengths
> of both deep learning and symbolic AI, coupled with a commitment to
> transparency and understandability, may pave the way for the development of
> AI systems that are not only more capable but also more aligned with the
> nuanced complexities of human intelligence and reasoning.
>
>
> -------- Forwarded Message --------
> Subject: Connectionists: Statistics versus “Understanding” in Generative
> AI.
> Date: Tue, 13 Feb 2024 09:54:48 -0800
> From: Gary Marcus <gary.marcus at nyu.edu> <gary.marcus at nyu.edu>
> To: Weng, Juyang <weng at msu.edu> <weng at msu.edu>
> CC: connectionists at mailman.srv.cs.cmu.edu
>
> ...
>
> A few sample visuals from those below (read the essays for sources). The
> argument in brief is that the systems do fine in statistically canonical
> situations, but lack depth in their comprehension of complex syntax,
> negation, unusual circumstances, etc. Much more context (and many more
> examples) in the essays themselves.
>
> Gary
>
>
>
> Gary
>
>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://mailman.srv.cs.cmu.edu/pipermail/connectionists/attachments/20240216/c8c6ebfd/attachment.html>