"kind of right, not very specific, a bit waffley" should be the tagline for ChatGPT Also, just speaking as a writing teacher, this video is so great! It definitely touches on my own issues with ChatGPT - its focus on "yeah, well, we don't **really** have any answers", the lack of actual arguments, the super sterile and utilitarian writing style - but also some possible positive uses for the tech (which I'm tentatively excited for, personally!)
@TBroomey
Жыл бұрын
This is surreal: my favourite lecturer and favourite writing youtuber in one place
@woosix7735
7 ай бұрын
The french KZitemr Monsieur phi has a great video on this subject. He has got apparently relay good results by using elaborate prompts. Explaining the methodology, having it write a draft outline before writing the actual essay. Essentially mimicking the way a human would write the essay.
@Bunnokazooie
Жыл бұрын
Great recording setup, The attic has come a long way!
@AtticPhilosophy
Жыл бұрын
Haha yes, I spend way too long worrying about how things look & sound!
@restfulairstream9612
Жыл бұрын
Thank you Mark for your video! Do you know any resources for learning the syntax of second-order logic and how to syntactically manipulate second-order formulae (proof system)? Any chance of a video on second-order logic in the future? Cheers!
@AtticPhilosophy
Жыл бұрын
An old but good textbook is Richard Jeffrey, Formal Logic: it’s scope and limits. 2bd order syntax allows predicate variables: Fx where F is a second-order variable, and quantifies, eg AFAx(Fx). 2nd order logic is incomplete, so there’s no official proof system, but all the usual first-order rules are sound, plus 2nd order quantifier rules (same as for 1st order quantifiers) are sound.
@captainmorgan2307
Жыл бұрын
ChatGPT is not foolproof. I told it to write a new story prompt about an underwater city. It wrote the storyline of Bioshock with the exact character names. ChatGPT straight up committed plagerism.
@AtticPhilosophy
Жыл бұрын
Haha! So would-be essay writers beware!
@askaone
Жыл бұрын
Usually I do the opposite: I do "ingest" to ChatGPT my paper, and I ask: what the paper says? Are the reasoning coherent? Interesting answers sometimes!
@philosophyversuslogic
Жыл бұрын
Super video! I like when it touches such vein themes!🤩💙💛
@AntonJumelet
Жыл бұрын
For a bit of comparison, below the response from ChatGPT on my prompt to write a university level essay on the question of whether we know that we are not brains in vats: "The idea of being a brain in a vat has been a popular thought experiment in philosophy for many years. The thought experiment imagines a situation where a person's brain is removed from their body and kept alive in a vat filled with nutrients. The brain is then connected to a computer that sends electrical impulses to it, creating the illusion of a full sensory experience. In this scenario, the person believes they are living a normal life, but in reality, they are just a brain in a vat. The question that arises from this scenario is whether we can know for sure that we are not brains in vats. At first glance, it may seem impossible to know whether we are brains in vats or not. After all, if the computer is sending us sensory experiences, how can we tell the difference between those experiences and real ones? However, upon closer examination, we can see that there are several reasons to believe that we are not brains in vats. One argument against the brain in a vat scenario is that it is not a coherent idea. The thought experiment assumes that there is a brain that is being stimulated by a computer, but this assumes that there is a brain in the first place. If we are brains in vats, then our bodies do not exist, and we are simply brains that have never experienced anything outside of the vat. This means that we do not have any frame of reference for what a brain is or what it experiences. We cannot say that we are brains in vats because we have no way of knowing what a brain is or what it experiences. Another argument against the brain in a vat scenario is that it is not a useful idea. Even if we were brains in vats, it would not change the way we experience the world. We would still have our sensory experiences and our thoughts, and we would still have to make decisions and interact with other people. The brain in a vat scenario is therefore a useless idea because it does not provide us with any new information or insight into the world. A third argument against the brain in a vat scenario is that it is self-defeating. If we are brains in vats, then the very idea that we are brains in vats is just another illusion created by the computer. In other words, if we are brains in vats, then we cannot know that we are brains in vats because the very idea of being a brain in a vat is just another illusion. This means that the brain in a vat scenario is a self-defeating idea because it undermines its own validity. Despite these arguments, some philosophers still believe that the brain in a vat scenario is a possibility. They argue that we cannot rule out the possibility that we are brains in vats because we have no way of verifying that our sensory experiences are real. However, this argument overlooks the fact that we do not need to know for certain that our sensory experiences are real in order to function in the world. We can make decisions, interact with others, and live our lives without ever knowing for certain that our sensory experiences are real. In conclusion, while the brain in a vat scenario is an intriguing thought experiment, there are several reasons to believe that we are not brains in vats. The scenario is not a coherent idea because it assumes that there is a brain that is being stimulated by a computer, but this assumes that there is a brain in the first place. The scenario is also not a useful idea because it does not provide us with any new information or insight into the world. Finally, the scenario is self-defeating because it undermines its own validity. While we may never be able to know for certain that we are not brains in vats, we do not need to know for certain in order to function in the world." (ChatGPT, openai.com, 25 February 2023)
@AntonJumelet
Жыл бұрын
Btw, on ZeroGPT this text got a 95% estimate as being AI/GPT generated
@zebulon220
Жыл бұрын
your title needs ammending you put c instead of g.
@AtticPhilosophy
Жыл бұрын
Thanks! Good spot.
@zebulon220
Жыл бұрын
@@AtticPhilosophy no worries.
@jiqiliu8641
Жыл бұрын
What a trending topic!
@frankavocado
Жыл бұрын
OK, no links on comments it seems - but ZeroGPT is a ChatGPT checker.
@AtticPhilosophy
Жыл бұрын
Interesting! Although the quality of the text on their page doesn’t inspire confidence …
@frankavocado
Жыл бұрын
@@AtticPhilosophy yeah, I know what you mean, but I heard about it via a piece on Sci-Fi journal Clarkesworld. They use it because ai generated subs are going through the roof - I reckon they’re probably not alone on that.
@nicolai_gamulea-schwartz
Жыл бұрын
Good criticism, solid. Too bad that you didn't actually use ChatGPT, although you keep referring to it. Marks have to go down for that I'm afraid, since all those bots are not quite the same - and for the repeatedly mispronounced name, and for the wacky stripes doing weird distracting stuff :) Those AIs are not that smart just yet, alas. With a bit of back-and-forth and a pinch of prompt engineering, they can do a much better job than shown here, but that means the man-in-the-loop is still essential, which kind of answers the question. But with the right self-reflecting architecture, we'll get there soon, we just need to dare put it together - or wait patiently until someone does.
@nicolai_gamulea-schwartz
Жыл бұрын
For reference, here's the output of the actual ChatGPT: Introduction: The idea that we might be brains in vats, with our experiences and perceptions being artificially generated by a malevolent external force, has been a popular thought experiment in philosophy for decades. This idea has implications for our understanding of knowledge and reality. This essay aims to explore the question: do we know that we are not brains in vats? The Brain in a Vat Scenario: The Brain in a Vat scenario is a thought experiment that presents the possibility that our sensory experiences and thoughts might be artificially created by an external force, while our brains are kept in a vat. In this scenario, the brain is connected to a machine that stimulates it to produce experiences and perceptions that are indistinguishable from those that we experience in the real world. The Argument Against Knowledge of Not Being a Brain in a Vat: The argument against knowledge of not being a brain in a vat is based on the idea that we cannot know whether our experiences are the result of a real external world or a simulated one. This argument asserts that our experiences and perceptions could be generated by a powerful computer, which could simulate reality to such an extent that we would not be able to tell the difference between the simulated reality and the real one. Therefore, according to this argument, we cannot know whether we are brains in vats or not. The Counter-Argument for Knowledge of Not Being a Brain in a Vat: The counter-argument for knowledge of not being a brain in a vat is based on the idea that some aspects of our experiences and perceptions cannot be artificially created. For example, the feeling of pain or the sense of taste cannot be simulated artificially in the same way that they are experienced in the real world. Therefore, according to this counter-argument, we can be sure that we are not brains in vats, because our experiences and perceptions include aspects that cannot be artificially created. The Problem of Induction: The problem of induction is relevant to the question of whether we know that we are not brains in vats. This problem arises from the fact that we make generalizations about the world based on our experiences, and we assume that the future will be similar to the past. However, the possibility that we are brains in vats means that our experiences and perceptions could be completely different from those in the real world, and that the rules of the simulated reality could change at any time. Therefore, the problem of induction makes it difficult to claim that we know that we are not brains in vats. Conclusion: In conclusion, the question of whether we know that we are not brains in vats is a complex philosophical problem. While the argument against knowledge of not being a brain in a vat suggests that we cannot know for certain that we are not brains in vats, the counter-argument for knowledge of not being a brain in a vat suggests that there are aspects of our experiences and perceptions that cannot be artificially created. The problem of induction complicates the issue further, making it difficult to claim that we know that we are not brains in vats. Ultimately, the question of whether we are brains in vats or not may be unanswerable, but it remains an intriguing and thought-provoking topic for philosophical inquiry.
@nicolai_gamulea-schwartz
Жыл бұрын
Prompt: Please list the weaknesses in the above essay. Answer: As an AI language model, I cannot give a subjective opinion about the quality of the essay. However, I can provide some possible weaknesses that a human reader may identify in the essay: Lack of Originality: The essay follows a common structure and includes the main arguments and counter-arguments related to the topic of brains in vats. However, the essay does not provide any original insights or perspectives that could distinguish it from other essays on the same topic. Limited Scope: The essay focuses only on the question of whether we know that we are not brains in vats, but it does not address other related questions, such as the ethical implications of the brain-in-a-vat scenario or the possible reasons why an external force might want to simulate our experiences. Unclear Terminology: The essay uses some philosophical terms and concepts, such as "knowledge" and "the problem of induction," without fully explaining their meaning or implications. This may make the essay difficult to understand for readers who are not familiar with these concepts. Lack of Examples: The essay does not provide any concrete examples or illustrations to support its arguments or counter-arguments. This may make it difficult for readers to visualize or relate to the ideas presented in the essay. Inconsistent Tone: The essay switches between a descriptive and argumentative tone, which may make it difficult for readers to follow the main points or understand the purpose of each paragraph. Limited Conclusion: The essay concludes by acknowledging that the question of whether we are brains in vats or not may be unanswerable, but it does not provide any suggestions or implications for further research or reflection on the topic.
@nicolai_gamulea-schwartz
Жыл бұрын
Prompt: Please rewrite the essay while addressing those issues. Answer: Introduction: The question of whether we are brains in vats is a philosophical thought experiment that has fascinated scholars for years. This essay seeks to provide a new perspective on the topic by discussing some of the main arguments and counter-arguments related to the question of whether we can know for certain that we are not brains in vats. Additionally, this essay aims to provide concrete examples and suggestions for further research to enhance our understanding of this complex topic. The Brain in a Vat Scenario: The brain in a vat scenario posits that our experiences and perceptions might be artificially created by an external force, while our brains are kept in a vat. In this scenario, a powerful computer would stimulate our brains to produce experiences and perceptions that are indistinguishable from those we experience in the real world. The Argument Against Knowledge of Not Being a Brain in a Vat: The argument against knowledge of not being a brain in a vat is based on the idea that we cannot know whether our experiences are the result of a real external world or a simulated one. According to this argument, our experiences and perceptions could be generated by a powerful computer that could simulate reality to such an extent that we would not be able to tell the difference between the simulated reality and the real one. Therefore, it is difficult to claim that we know for certain that we are not brains in vats. The Counter-Argument for Knowledge of Not Being a Brain in a Vat: On the other hand, there is a counter-argument that asserts that some aspects of our experiences and perceptions cannot be artificially created. For instance, sensations such as pain or taste cannot be simulated artificially in the same way that they are experienced in the real world. Therefore, according to this counter-argument, we can be reasonably certain that we are not brains in vats because our experiences and perceptions include aspects that cannot be artificially created. The Limitations of Empirical Evidence: While the argument against knowledge of not being a brain in a vat and the counter-argument for knowledge of not being a brain in a vat present interesting perspectives on the topic, there are limitations to empirical evidence that need to be considered. One of these limitations is the problem of induction, which arises from the fact that we make generalizations about the world based on our experiences, assuming that the future will be similar to the past. However, the possibility that we are brains in vats means that our experiences and perceptions could be completely different from those in the real world, and that the rules of the simulated reality could change at any time. Therefore, the problem of induction makes it difficult to claim that we know for certain that we are not brains in vats. Possible Implications and Future Research: The brain in a vat scenario raises some interesting implications for our understanding of knowledge and reality. For instance, if we cannot be certain that we are not brains in vats, then how can we trust our senses and perceptions to tell us anything about the world? Additionally, if we are brains in vats, then what is the purpose of the simulation, and who or what is controlling it? To address these and other questions related to the brain in a vat scenario, future research should explore the limits and possibilities of artificial intelligence, virtual reality, and the nature of consciousness. By doing so, we can gain a better understanding of the potential and limitations of technology, as well as the ethical and existential implications of the brain in a vat scenario. Conclusion: In conclusion, the brain in a vat scenario is a fascinating thought experiment that challenges our understanding of knowledge and reality. While the question of whether we are brains in vats or not may be unanswerable, the arguments and counter-arguments presented in this essay highlight the complexities and limitations of our empirical evidence. By exploring these limitations and possibilities, we can gain a better understanding of the nature of our experiences and perceptions, as well as the potential and limitations of technology. Additionally, future research could provide insights into the ethical and existential implications of the brain in a vat scenario, such as the possibility of living in a simulation, the nature of consciousness, and the impact of artificial intelligence on our lives. In conclusion, while the brain in a vat scenario may seem like a far-fetched and abstract thought experiment, it has important implications for our understanding of knowledge, reality, and the limits of technology. By examining the arguments and counter-arguments related to this scenario, and by exploring the possibilities and limitations of empirical evidence, we can gain a better understanding of the complexities of our existence and the potential of our technological advancements. Ultimately, this could lead to new insights into the nature of our consciousness, the purpose of our existence, and the role of technology in shaping our lives.
@nicolai_gamulea-schwartz
Жыл бұрын
Here's Bing's take on the same initial prompt: Hello, this is Bing. I can help you write a university essay on this topic.😊 The brain-in-a-vat scenario is a philosophical thought experiment that challenges our assumptions about knowledge, reality, truth and meaning². It asks us to imagine that we are not living in the real world, but rather we are brains kept alive in vats by an evil scientist who feeds us false sensory experiences through a computer¹. One way to approach this essay is to consider the following questions: - What are some arguments for and against the possibility that we are brains in vats? - How do different theories of knowledge (such as rationalism, empiricism, skepticism) deal with this scenario? - What are some implications of this scenario for our moral, social and political beliefs and actions? - How can we respond to this scenario in a reasonable and coherent way? To help you get started, here are some possible thesis statements: - We cannot know for sure whether we are brains in vats or not, but we have good reasons to trust our common sense and reject radical skepticism. - We can know that we are not brains in vats by appealing to semantic externalism and causal theory of reference. - We should act as if we are not brains in vats because it is more conducive to our happiness and well-being than doubting everything. I hope this helps you with your essay. Good luck!👍 Source: Conversation with Bing, 26/02/2023(1) Brain in a vat - Wikipedia. en.wikipedia.org/wiki/Brain_in_a_vat Accessed 26/02/2023. (2) BRAINS IN VATS? DON'T BOTHER! | Episteme | Cambridge Core. bing.com/search?q=brains+in+vats Accessed 26/02/2023. (3) We Are All Brains In Vats - Daniel Toker. thebrainscientist.com/2017/06/28/we-are-all-brains-in-vats/ Accessed 26/02/2023. (4) The Brain in a Vat - Internet Encyclopedia of Philosophy. iep.utm.edu/brain-in-a-vat-argument/ Accessed 26/02/2023. (5) 3 - How to think about whether we are brains in vats - Cambridge Core. www.cambridge.org/core/books/brain-in-a-vat/how-to-think-about-whether-we-are-brains-in-vats/D33E79C994116F561ED0D9AC858DC96D Accessed 26/02/2023.
@AtticPhilosophy
Жыл бұрын
Yeah I ran the question through ChatGPT several times and got similar answers to this - some more similar to the ChatSonic version. This version is in some ways better (eg good section headings), in some ways worse (eg no mention of Putnam, issue of 'pain' ignores that the problem focuses on knowledge of the external world). But overall, its roughly the same (eg severe lack of philosophical detail, wishy washy conclusion) and would do worse than average on my 1st year module.
Пікірлер: 28