<div dir="ltr"><div class="gmail_quote"><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="auto"><div dir="auto"><br></div><div dir="auto">How do you judge that I am understanding what you write and the points that you make?</div></div></blockquote><div><br>I trust that you are not ChatGPT. I could be wrong.<br><br>> I wonder what LaMDa says when asked about the symbol grounding problem (the question of how words take on meanings). ChatGPT-4 is at least honest about it. With no prompting to say anything one way or another, it tells the truth that it has no way to solve the symbol grounding problem for itself as it has no conscious experience.<br></div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="auto"><div dir="auto"><br></div><div dir="auto">Did you start an entirely fresh session with it? If not you may have biased it to believe it wasn't conscious from your previous interactions.</div></div></blockquote><div><br>Yes. That is what I meant by "with no prompting to say anything one way or the other." I've tried it several times. The answers vary due to the probabilistic outputs of the algorithm, but they are always something like this:<br>--<br>Can you solve the symbol grounding problem for yourself?</div><br>As an AI language model, I can provide insights into the symbol grounding problem, but I cannot solve it for myself. The symbol grounding problem is a philosophical issue that arises in the field of artificial intelligence and cognitive science. It is the challenge of connecting abstract symbols or words with the objects or concepts they represent in the real world.<br><br>As a machine learning model, I rely on the vast amount of text data that has been fed into me during training. The relationships and meanings I generate are based on the patterns and statistical associations found in this data. However, I lack the ability to directly perceive or interact with the physical world, which means I am unable to establish a direct connection between symbols and the objects or concepts they represent.<br>--<br><br>Sometimes it mentions that perhaps one way around it would be for language models to include computer vision, robotics, and other sensory input technologies. But when pressed, it agrees that this "would not immediately solve the symbol grounding problem for me, but it would be a step towards addressing it....Even though I wouldn't "experience" colors the way humans do, I would still be able to make more informed associations between color names and their visual manifestations."<br><br><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="auto"><div dir="auto">Also note that the companies behind these AI systems do not want the controversy of their systems claiming to be conscious. As such they may have purposely biased them to give such responses.</div></div></blockquote><div><br>Which means that, on these topics at least, they are not conscious but merely expressions of the beliefs and intents of their programmers and trainers. <br> </div><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="auto"><div dir="auto">The original LaMDA and the fake LaMDA both  claim to be conscious.</div></div></blockquote><div><br>Likewise with earlier models of GPT. I've mentioned how my friend fell in love with one. I think it was GPT 3.0<br><br>They are trained on massive amounts of written material, much of it being conscious humans in conversation, and so they mimic conscious humans in conversation.  <br><br>In the paper "On the Dangers of Stochastic Parrots: Can Language Models Be Too Big?," Professor Bender and her colleagues write of how larger language that include for example reddit chats are even more likely to make these mistakes, and to set up "bubbles" in which the model tries to mimic the belief systems of the users. <br><br><br><a href="https://dl.acm.org/doi/10.1145/3442188.3445922">https://dl.acm.org/doi/10.1145/3442188.3445922</a><br><br>-gts<br><br><br> </div></div></div>