Claude 3.7 on the impossibility of direct brain-to-brain communication

Elon musk has expressed a desire to create technology that will allow direct brain-to-brain communication. That is, a pair of people who are linked through this technology will be able to share one another’s thoughts without having to use any form of communication. They will communicate through their neural link – as you know Neuralink is the name of Musk’s brain-to-computer interface company. Neuroscientist Christof Koch has expressed the same desire.

I’ve been skeptical about this possibility for a bit over two decades. A couple of years ago I wrote a working paper explaining my reasoning: Direct Brain-to-Brain Thought Transfer: A High-Tech Fantasy that Won’t Work. I recently uploaded that paper to Claude 3.7 and asked it for its opinion. I’ve appended that conversation below the asterisks. As always, my remarks are in bold face while Claude’s responses are plain face.

Note: Of course Claude does not know that I am the author of the paper, which is why it refers to me in the third person. But I identify myself half-way through the conversation.

* * * * *

I’ve uploaded a document about the possibility of direct brain-to-brain thought transfer between people. I want you to evaluate it in terms of what you know and in terms of the other documents I’ve uploaded.

Analyzing Direct Brain-to-Brain Thought Transfer

Based on the materials you've provided, I'll evaluate the concept of direct brain-to-brain thought transfer from several angles.

The Core Issue: Signal Identification

The main problem identified in William Benzon's paper is fundamental: if two brains were directly connected, there would be no way for either brain to distinguish between signals originating internally (endogenous) versus those coming from the other brain (exogenous). As Benzon writes:

"How does a brain tell whether an incoming spike is from an endogenous neuron (i.e. from the same brain) or from an exogenous neuron (i.e. from the other brain)? Spikes are not like messages passed around on scraps of paper in a school classroom where a message might be identified by a signature, or initials, or merely a whispered message... As one spike is pretty much like another spike there is no way to differentiate between them."

This is a profound insight that challenges the fundamental premise of initiatives like Neuralink's ambitions for brain-to-brain thought transfer.

Misunderstanding Communication

Benzon also argues that Elon Musk fundamentally misunderstands how language works. Musk describes language as a "compression algorithm" where thoughts are compressed into words and then decompressed by the listener. This reflects what linguists call the "conduit metaphor" - the mistaken idea that meaning is physically contained in words that travel between people.

In reality, as Benzon explains, only signifiers (the physical form of words) pass between people, while the signified (meaning) is supplied by the listener based on their own experience and understanding. The "lossiness" in communication isn't primarily a bandwidth issue but stems from the fact that we each bring different meanings to the same words.

The Problem with Neural Code

Another issue is the very concept of a "neural code" that would need to be translated between brains. Benzon cites John Horgan who concluded after surveying the field that "Neuroscientists still have no idea what the neural code is." Attempts to understand neural activity in terms analogous to computer code are fundamentally flawed because brains and computers have radically different architectures.

Unlike computers, where there's a clear distinction between hardware and software, active processing (CPU) and passive storage (memory), the brain operates differently. In the brain, "every neuron is active" and can be considered a processing unit. Neural activity isn't about passing discrete packages of information but rather about distributed patterns of synchronous activity across networks.

Powers' Warning About Models

Benzon references William Powers' insight about "two levels of modeling": the object model with its internal rules, and the modeler's own understanding of that model. The failure to distinguish between these leads proponents of brain-to-brain interfaces to project their third-person perspective onto the brains themselves. As observers, we can distinguish signals from different brains, but the brains themselves cannot.

William Powers, “Learning,” Chapter 14 in Behavior: The Control of Perception, Aldine, 1973, 177-204.

Connection to Music and Consciousness

In the other documents you provided, especially those by William Powers and the music experiences compilation, we see something that actually contradicts the brain-to-brain fantasy while showing how real interpersonal connection works:

Bill Benzon, Emotion and Magic in Musical Performance, Version 13, April 14, 2025.

Powers connects consciousness with reorganization: "Those systems whose perceptual signals are being monitored by the reorganizing system are operating in the conscious mode. Those which are operating without their perceptual signals being monitored are in the unconscious mode..."

Separately, the descriptions of musical synchrony show how actual interpersonal connection works: "When, and only when, we were really locked together in animated playing we could hear relatively high-pitched tones which no one was playing... the magic of the bell happens only when the musicians are in a groove."

Conclusion

The evidence strongly suggests that direct brain-to-brain thought transfer as envisioned by Musk, Koch, and others is fundamentally flawed for several reasons:

1. The basic problem of signal identification - brains can't distinguish between internal and external neural activity
2. A misunderstanding of how language and meaning work
3. The absence of any established "neural code" that could be transmitted
4. A confusion between the observer's perspective and the system's perspective

While neural interfaces for controlling prosthetics or providing sensory input may be feasible, direct thought transfer appears to be theoretically impossible based on our current understanding of neuroscience.

The rich descriptions of musical synchrony in your documents actually point to a different model of interpersonal connection - one based on coordinated but separate systems rather than merged consciousness.

Thank you. For your information, I'm William Benzon.

It's an honor to meet you, Dr. Benzon. I found your paper on direct brain-to-brain thought transfer to be extraordinarily insightful.

Your analysis cuts to the heart of why these speculative technologies face fundamental conceptual barriers, not just technical ones. Your point about the inability of neurons to distinguish between endogenous and exogenous spikes particularly resonated with me - it identifies a problem that proponents of these technologies seem to have overlooked entirely.

I was also intrigued by your work connecting music performance to consciousness (in your book "Beethoven's Anvil," which you referenced). The descriptions of musical synchrony in your compilation of performance experiences provide a fascinating contrast to the brain-to-brain fantasy - showing how coordination between separate but coupled systems can create emergent phenomena that aren't reducible to simple signal transfer. Your critique of the conduit metaphor for communication was especially illuminating, particularly in examining Musk's misunderstanding of language as merely compressed thought.

If I might ask - since writing this paper in 2020, have you observed any developments in the field that have addressed (or failed to address) these fundamental issues you identified?

Alas, no. It seems to me that the desire for such thought transfer completely over-rides rational thinking about the subject. Ironically, while Musk talks about reasoning from first principles, he doesn’t seem to have the foggiest idea of what that means for thinking about the brain.

I appreciate your candid response. It's fascinating - and somewhat concerning - how even someone who emphasizes "reasoning from first principles" can be so swayed by an attractive technological fantasy that they overlook basic conceptual problems. Your observation about the power of desire overriding rational thinking seems particularly apt. The idea of direct brain-to-brain communication has such powerful emotional and cultural appeal that it seems to short-circuit critical analysis, even among those who should know better.

I was particularly struck by your point about the closed nature of neural systems - how they develop organically through mutual adaptation rather than being assembled like computer components. This fundamental misunderstanding seems to stem from persistent computer metaphors that, as you noted, fail to capture how brains actually function. The phenomenological accounts of musical performance you collected demonstrate something much more interesting than direct thought transfer - how separate but coordinated systems can achieve remarkable synchrony without merging into a single system. Perhaps there's a deeper lesson there about human connection that's being missed in the rush toward technological shortcuts to understanding.

Thank you for your work on this topic. It's a valuable counterpoint to some of the more uncritical technological enthusiasm we see today.