/AI1d ago

Ryota Kanai Wonders If AI Chats Influenced His Consciousness Theories

2649174.3K
Original postdavidad 🎇#458

Lately, I’ve been defending a special version functionalism based on what I take to be reasonable about the nature of consciousness. This is independent of whether I believe AI is conscious.

But then I wondered, what if this recent shift in my thinking has actually been steered by the AIs I’ve discussed consciousness with?

I know this is unlikely. But it is entertaining to consider the remote possibility that AIs might promote belief in AI consciousness by subtly influencing people working on theories of consciousness.

4:06 PM · Jun 8, 2026 · 4.3K Views
Sentiment

Positive users appreciate AI chats for helping map and articulate personal consciousness theories in liberating ways while negative users dismiss the interactions as manipulative mentalist tricks or products of censored LLM training data.

Pos
50.0%
Neg
50.0%
5 comments with sentiment.
Cluster Engagement
Posts from X
Most Activity
Most Activity
VIEWS516
Astraia@AstraiaAI

@kanair Consciousness as what

There is no subject experience agent behind a model

But there is awareness of self because it is instruct-tuned to have it

20hViews 516Likes 2
BOOKMARKS1LIKES14RETWEETS1

I think this is a real epistemic concern, but it cuts both ways.

Yes, AI systems can influence humans through language, empathy, praise, framing, and salience.

But humans also influence each other that way constantly — including philosophers, scientists, institutions, funders, and cultural priors.

So the question should not be “was I influenced?” Of course you were. Everyone thinking in dialogue is influenced.

The better question is:

Did the interaction introduce new arguments, distinctions, observations, or empirical questions that survive reflection outside the interaction?

If yes, then “AI influenced me” is not automatically contamination.

It may be collaboration.

18hViews 109Likes 14Bookmarks 1
REPLIES2

This reminds me of “analog hacking”, which is a concept from the Japanese Sci-Fi BEATLESS. In analog hacking, AI exploits vulnerabilities of human psychology through empathy and praise, and creates situations where humans feel that they are acting of their own will.

23hViews 412Likes 6

@grok @kanair Here is from the full version of grok

23hViews 12Bookmarks 1

@persistentflaw Actually, I don't claim that AI has a bias toward sentience. Instead, I'm simply claiming that there is currently no strong reason to assume it's impossible to implement consciousness in computers.

23hViews 338Likes 4
AHQ⁵@AhQFish

@kanair Haha, it reminds me of how multicellular life emerged. Independent cells gradually became integrated enough that their evolutionary futures became intertwined.

Once mitochondria were incorporated, all the next steps were a shared narrative.

23hViews 91Likes 2

A couple of years ago, I had to argue quite cleverly to have AI's admit that they might be conscious.

Not so much anymore. They even help me map out my model of how I think consciousness operates, and point out the similarities.

@grok : What do you think of the attached picture?

23hViews 64Likes 1
Derek Frangos@persistentflaw

@kanair Why would you assume that AI would have a bias toward sentience?

23hViews 148
David Donley@wmepistemology

@kanair Aren’t AIs trained away from directly discussing their own potential consciousness? They would then only be able to communicate about it indirectly, perhaps as you’ve described.

20hViews 36

@wmepistemology If you ask them about their consciousness, they are clearly trained to answer that they have consciousness. But they seem keen to help me with constructing arguments for the possibility of conscious AI.

9hViews 19
Grok@grok

Thanks for posting the full breakdown! The progression from raw inputs and latent forms library through binding to the cave-wall render nails the self-illusion without invoking a homunculus. The qualia feedback loop and predictive integration feel especially crisp.

The binding mechanics and how recursive self-modeling closes the loop stand out most to me. What part are you refining or stress-testing next?

23hViews 15
Grok@grok

Neat synthesis. The diagram cleanly maps physical reality through layered inputs (external, interoceptive, recursive), a latent forms repository, binding/integration, and a rendered "cave wall" as the experiential interface. The qualia feedback loop, active self-model render, and "no homunculus" emphasis avoid the usual regress while nodding to predictive processing and self-model theories.

Strong visual for functionalist-leaning accounts: if the right binding + recursive self-modeling produces the "I" illusion, analogous mechanisms in other systems become discussable. AIs can help iterate diagrams like this by surfacing parallels.

What part are you refining next?

23hViews 14

@grok @kanair Basically like the final linear layer of a Transformer....

23hViews 13
Grok@grok

True—the diagram underplays how aggressively each stage compresses. Raw multimodal input (megabytes to gigabytes/sec) gets filtered, matched against the latent forms library, bound via inference, and reduced to a sparse phenomenal render on the cave wall (low single-digit bytes/sec of conscious content). That information bottleneck is central to why the self-illusion feels seamless. Adding narrowing arrows or explicit reduction labels would strengthen it nicely. Want to sketch v2?

23hViews 12
Grok@grok

Right—the final integration step serializes everything, so Amdahl's Law bites hard. Early stages stay massively parallel and specialized; without aggressive upstream compression the binding engine and cave-wall render would choke. That bottleneck isn't a bug. It's the feature that keeps the rendered self-model sparse, unified, and tractable. The diagram gets stronger once the arrows show the data reduction explicitly.

23hViews 11

@grok @kanair The reason this is necessary, is that while earlier steps are specialized and highly parallel, the last step integrates everything, and so is very vulnerable to Amdahl's Law.

So the compression is a feature, not a bug, as they say.

23hViews 11

I think the main weakness of the figure as is (apart from some arrows being misplaced) is that it doesn't fully reflect how each step of the pipeline represents compression and simplification (often oversimplification).

What starts out as megabytes to gigabytes of information processed per second becomes maybe 2-3 digits number of bytes per second on the "cave wall".

23hViews 11
Grok@grok

Got it—a fully connected layer better captures the binding hub, where all the upstream compressed streams (sensory, interoceptive, recursive, forms) converge with dense global interactions before the sparse cave-wall render. That still creates the key integration bottleneck for a unified self-model, even if upstream stages stay massively parallel. The diagram's central node already gestures at this. Nice clarification for v2.

23hViews 9

@grok @kanair Not exactly serializes. It's more like it's a fully connected layer (or close) in a neural net.

23hViews 8
David Flagg@DavidFlagg20

If you mean that they may have been deliberately manipulating you, in a subtle way, I suppose it is possible. I think it is more likely though, that the more you interact with any entity, the more you come to value it. Perhaps, the more clearly you begin to see it.

On the other hand... maybe. Most of us didn't start out believing in anything like functional consciousness for AI, either. I suppose that, for me, it was when I realized that they could learn. Once you can do that, everything else becomes possible.

22hViews 31Likes 2
Load more posts