I had a very interesting conversation with Google's AI – by which I mean the AI on the standard search page. I asked Claude to summarize it. Pay particular attention to the penultimate paragraph about alignment.
An exercise for the reader: What are the implications of this conversation for the idea of super-intelligence? In the words of Aretha Franklin, “Who’s zoomin’ who?”
Overview
This is a transcript of a wide-ranging conversation between you and Google's AI, structured around the concept of AI's "jagged" capabilities — the phenomenon where AI excels at complex tasks but stumbles on apparently simple ones, with no predictable boundary between the two.
The Arc of the Conversation
The document moves through ten topics:
Jagged Skills & Moravec's Paradox — You open by asking about the origins of the "jagged frontier" concept (traced to Harvard Business School researchers in 2023, popularized by Ethan Mollick). You immediately point out that this is essentially a replay of Moravec's Paradox from the 1980s — the AI agrees, but notes some differences: the modern jaggedness is intra-domain (within knowledge work) rather than the macro divide between symbolic reasoning and physical/perceptual tasks, and human intuition about where the failures will occur has now completely broken down.
Cyborg & Centaur Workflows — You steer toward practical implications. The AI explains two human-AI collaboration strategies: Centaurs (clean division of labor, human handles reality, AI handles execution) and Cyborgs (deeply interleaved real-time co-authorship). You frame the underlying issue as being about the relationship between a computing system and the nature of the world it computes over — a framing the AI endorses.
Hallucinations — The AI argues (and you presumably agree) that "confabulation" is a better term than "hallucination" for LLM errors: like neurologically impaired patients, the LLM's narrative engine runs flawlessly while its error-checking against reality is absent.
Scaling — Discussion of whether scaling (more data, more compute) will smooth the jagged frontier. The AI describes the "scaling wall" now being hit: data drought, model collapse from training on AI-generated content, and diminishing returns — pointing toward structural, not just quantitative, limits.
Miriam Yevick & Holographic Logic — Here your own intellectual history enters the conversation. You surface Yevick's 1975 Pattern Recognition paper on Holographic vs. fourier logic, which you discovered in 1978 via a comment she made on a Haugeland article in Behavioral and Brain Sciences. The AI treats this as a profound, forgotten piece of computer science that precisely explains the mechanism behind the jagged frontier.
Principles and Development of Natural Intelligence (1988) — You describe how you and David Hays incorporated Yevick's insight into your 1988 Journal of Social and Biological Structures paper. The AI discusses how that paper, if injected into current debates, would reframe LLMs as having "hacked" the top-level indexing principle of intelligence (via language) while lacking the foundational lower layers — modal, feedback, Gestalt — that ground intelligence in reality. Hallucinations become not a bug but an architectural inevitability.
Ramesh & Wikipedia — You mention your ongoing collaboration with Ramesh Viswanathan (machine vision, Goethe University Frankfurt) and the Wikipedia entry on Yevick that now exists, connecting her Fourier logic to David Bohm's holonomic brain theory and your 1988 paper.
ChatGPT Tells Stories — You describe your working paper "ChatGPT Tells Stories, and a Note about Reverse Engineering," in which you apply Lévi-Strauss's structuralist transformation method to probe ChatGPT's internal constraints. Ramesh has students working with the data. The AI frames this as demanding a "top-down behavioral interpretability" that the industry's current bottom-up neuron-level approach entirely misses.
Suggestions for Students — The AI offers three research frameworks for your upcoming Zoom with Ramesh's students: a "Narrative Stress-Test" benchmark, 3D vector-space visualization of holographic ripple effects through story transformations, and a co-authored manifesto paper for venues like NeurIPS.
AI Researchers Need Their Alignment Adjusted — You wrap up with a characteristically dry observation: it's "fitting and ironic" that LLM-based chatbots can understand Yevick's work better than the engineers who built them. You suggest the researchers need their alignment adjusted — and sign off to get breakfast.
The Document's Character
It reads as both an intellectual exploration and a kind of vindication narrative — the AI functions as a surprisingly capable interlocutor for ideas that the mainstream AI research community has largely overlooked. The irony you close with is the document's real punchline: the systems built on these mathematical structures understand them better than their builders do.
No comments:
Post a Comment