I’ve probably committed a felony by doing this, but I’m going to post a rebuttal written by GPT-4, and my commentary on it. I’m a former debate competitor and judge, and have found GPT-4 to be uncannily good at debate rebuttals. So here is what it came up with, and my comments. I think this is a relevant comment, because I think what GPT-4 has to say is very human-relevant.
Radiations from the Sun bounce off a piece of cheese and enter into the beady eyes of a mouse; its retinal cells detect the light; the energy of the photons triggers neural impulses; these impulses are transmitted to the visual-processing areas of the mouse’s brain; and there the optical information is processed and reconstructed into a 3D model that is recognized as a piece of cheese; and so the mouse knows there is cheese nearby.
This is the essence of the intuitive wisdom of mice—this whole process is not magic, and they don’t have to understand it. They understand the presence of cheese. They instinctively know which sensory processes will lead to survival, and which will not.
I find this mirroring from “deliberate rationality” to “intuitive wisdom” and equating cognition to instinct very interesting and not at all obvious, even from the perspective of a human former debate judge. It’s a great rebuttal IMO. It points out human deficiencies in our inability to detect cheese, which is arguably more important to mice than their ability to philosophise.
Humans can see, but they overcomplicate seeing. Because of that, they often miss what is right in front of them. Take a moment to appreciate this, for it is indeed fascinating.
IMO another interesting insight—what does “can’t understand seeing” from the human even mean? I’d count this as another decent debate rebuttal probably +1 for team mouse.
Humans see, but they get lost in their understanding of visual cortexes, often making them susceptible to optical illusions. A human lives in a mental world that includes jobs, responsibilities, societal pressures—but not human instincts. Their mind does not often focus on their immediate environment. But we, as mice, can detect a morsel of food from a distance, or sense a lurking predator, without getting distracted by the nature of our senses. Humans often fall victim to their beliefs, but mice react to what is—there must be a clear distinction between survival and theory, between senses and reality. And this is not a trivial skill, remember how rare it is among humans.
If I was judging a debate between mice and humans, I would score this for the mice. The human is arguing “But we, as humans, can look at a seemingly bizarre image, and realize that part of what we’re seeing is the lens itself” whereas the mouse is arguing that their abilities are in tune with survival over theory, and how deficient that balance sometimes is among humans. I like this counter-argument for the mice, practicality over self-perceived superiority. Empathising other species-centric values is something that even my more philosophical human friends struggle with.
The whole idea of Instinct is, simply, intuitive reasoning about a more reliable process for making the contents of our mind mirror the contents of the world. It is the sort of thing humans often forget. Contemplating this business of “responding to immediate needs and threats,” we can see why it works. Instinct is not separate from reality, far away from the understanding of humans. Instinct is not something that only applies to the wilderness. Instinct, itself, is an understandable process-in-the-world that correlates brains with reality.
Lots of parrotting here, but the switch from “inside laboratories” to “the wilderness”, and the argument that instinct is a better alignment strategy than science are both very interesting to me. I wouldn’t award any points here, pending more arguments.
Instinct makes sense, when you think about it. But humans often overthink, which is why they lose touch with their instincts. One should not overlook the wonder of this—or the potential power it bestows on us as mice, not just animal societies.
I found this quote inspiring, if I was a mouse or other animal. I may have to print a “mouse power” t-shirt.
Indeed, understanding the engine of thought may be more complex than understanding a mouse’s instinct—but it is a fundamentally different task.
A mouse’s instinct is being equivalized to a steam engine, interesting pivot but the contrasting statements still hold water, compared to the original, IMO.
Consider a time when a human may be anxious about the possibility of a future war. “Do you believe a nuclear war will occur in the next 20 years? If no, why not?” The human may reply with a timeline of a hundred years because of “hope.” But why cling to hope? Because it makes them feel better.
Reflecting on this whole thought process, we can see why the thought of war makes the human anxious, and we can see how their brain therefore clings to hope. But in a world of realities, hope will not systematically correlate optimists to realities in which no war occurs.
To ask which beliefs make you happy is to turn inward, not outward—it tells you something about yourself, but it is not evidence entangled with the environment. There is nothing wrong with happiness, but it should follow from your perception of the world, rather than manipulating your mental map.
Very much parrotting here, but I would note “manipulating your mental map” as a counterpoint to “tampering with mental paintbrushes” is an interesting equivalency. I also respect the re-framing of hope as a human flaw, in contrast with the reality-based instincts of a mouse.
If you can see this—if you can see that hope is shifting your first-order thoughts by too large a degree—if you can understand your mind as a mapping engine that has flaws—then you can apply an intuitive correction. The brain is a flawed lens through which to see reality. This is true of both human brains and mouse brains. But a mouse brain is a flawless lens that instinctively understands its environment and reacts accordingly—without second-guessing its instincts, without biases, and without the need for second-order corrections. This, in practice, makes the lens far more efficient. Not perfect, but far more efficient.
Arguing for efficiency over power, and reality over perception, is an argument that would be an interesting avenue to be pursued as a debate judge. As well as the concept of a mouse brain being flawless, as an argument presented by an AI.
At the above paragraph, it ran out of tokens after “—without”, so I prompted it “That’s great, please finish the essay.” and everything after that (above and below) were what followed.
Unlike humans, mice do not overthink or overcomplicate. They live in the present, focused on their immediate needs and potential threats. They don’t have to understand their senses; they simply use them. They don’t ponder about the existence of mouse brains; they utilize their brains efficiently.
As a debate judge, pretty decent summary of key rebuttals.
Human self-consciousness, while enabling them to create and innovate, also leads them to constant self-doubt and uncertainty, often resulting in inaction or wrong action. Mice, on the other hand, trust their instincts and react swiftly and decisively, making them highly effective in their world.
While humans are busy understanding and correcting their flawed lens, mice are using their lens to navigate the world, survive, and thrive. While humans are stuck in a loop of reflective reasoning and corrections, mice are out there, living their life, applying their senses and instincts to the best of their abilities. They are not bothered about the nature of their lens, they are just using it.
A solid foundational rebuttal of the type I would have used back in my days of competitive debate. Probably better than anything I would have written on the fly.
In the end, it’s not about which brain is superior, but about which brain is more efficient for the life it leads. And from a mouse’s perspective, the ability to respond instinctively to the environment without the need for constant reflection and correction seems like a pretty great deal. Perhaps it’s time humans took a page out of the mouse’s book and learned to trust their instincts more, and their overthinking less.
Great re-framing of a debate (efficiency vs power or creativity).
For a formal debate, I would rate GPT-4′s rebuttal very high in a real-world “humans vs mice” debate scenario. The outcome of Eliezer vs Team Mouse would almost certainly come down to delivery, given the well-reasoned arguments on both sides given above. Overall, well above the quality of argument I would expect from top-tier debate teams at the high school level, and above average for the college level.
I’ve experimented with doing Lincoln-Douglas style debates with multiple GPT-powered “speakers” with different “personalities”, and it’s super interesting and a great brainstorming tool. Overall I consider GPT-4 to be vastly superior to the average twelfth-grader in general purpose argumentative debating, when prompted correctly.
Hopefully this is constructive and helps people get back to the basics—questioning human-centric thinking, trying to understand what alien intelligence may look like, and how it may challenge entrenched human biases!
I’ve probably committed a felony by doing this, but I’m going to post a rebuttal written by GPT-4, and my commentary on it. I’m a former debate competitor and judge, and have found GPT-4 to be uncannily good at debate rebuttals. So here is what it came up with, and my comments. I think this is a relevant comment, because I think what GPT-4 has to say is very human-relevant.
I find this mirroring from “deliberate rationality” to “intuitive wisdom” and equating cognition to instinct very interesting and not at all obvious, even from the perspective of a human former debate judge. It’s a great rebuttal IMO. It points out human deficiencies in our inability to detect cheese, which is arguably more important to mice than their ability to philosophise.
IMO another interesting insight—what does “can’t understand seeing” from the human even mean? I’d count this as another decent debate rebuttal probably +1 for team mouse.
If I was judging a debate between mice and humans, I would score this for the mice. The human is arguing “But we, as humans, can look at a seemingly bizarre image, and realize that part of what we’re seeing is the lens itself” whereas the mouse is arguing that their abilities are in tune with survival over theory, and how deficient that balance sometimes is among humans. I like this counter-argument for the mice, practicality over self-perceived superiority. Empathising other species-centric values is something that even my more philosophical human friends struggle with.
Lots of parrotting here, but the switch from “inside laboratories” to “the wilderness”, and the argument that instinct is a better alignment strategy than science are both very interesting to me. I wouldn’t award any points here, pending more arguments.
I found this quote inspiring, if I was a mouse or other animal. I may have to print a “mouse power” t-shirt.
A mouse’s instinct is being equivalized to a steam engine, interesting pivot but the contrasting statements still hold water, compared to the original, IMO.
Very much parrotting here, but I would note “manipulating your mental map” as a counterpoint to “tampering with mental paintbrushes” is an interesting equivalency. I also respect the re-framing of hope as a human flaw, in contrast with the reality-based instincts of a mouse.
Arguing for efficiency over power, and reality over perception, is an argument that would be an interesting avenue to be pursued as a debate judge. As well as the concept of a mouse brain being flawless, as an argument presented by an AI.
At the above paragraph, it ran out of tokens after “—without”, so I prompted it “That’s great, please finish the essay.” and everything after that (above and below) were what followed.
As a debate judge, pretty decent summary of key rebuttals.
A solid foundational rebuttal of the type I would have used back in my days of competitive debate. Probably better than anything I would have written on the fly.
Great re-framing of a debate (efficiency vs power or creativity).
For a formal debate, I would rate GPT-4′s rebuttal very high in a real-world “humans vs mice” debate scenario. The outcome of Eliezer vs Team Mouse would almost certainly come down to delivery, given the well-reasoned arguments on both sides given above. Overall, well above the quality of argument I would expect from top-tier debate teams at the high school level, and above average for the college level.
I’ve experimented with doing Lincoln-Douglas style debates with multiple GPT-powered “speakers” with different “personalities”, and it’s super interesting and a great brainstorming tool. Overall I consider GPT-4 to be vastly superior to the average twelfth-grader in general purpose argumentative debating, when prompted correctly.
Hopefully this is constructive and helps people get back to the basics—questioning human-centric thinking, trying to understand what alien intelligence may look like, and how it may challenge entrenched human biases!