<div dir="ltr">GPT-4 drew an ASCII circle for me when I asked. I then asked the following:<br> <br>Q: Never having been trained visually on the shapes of apples and pears, how can a large language model draw their shapes and distinguish between them?<br><br>A: As a large language model, I am purely text-based and do not have the ability to see, process, or create visual images like drawings. However, I can try to describe the shapes of apples and pears, as well as help you distinguish between them using textual descriptions.<br><br>Apples are generally round, sometimes with a slightly flattened top and bottom. They may have a small indentation at the top, where the stem connects to the fruit, and a shallow, star-shaped indentation at the bottom, where the apple's calyx is located. The skin of an apple can be smooth or slightly bumpy and comes in various colors, such as red, green, or yellow.<br><br>Pears, on the other hand, have a unique shape. They are wider at the bottom and taper towards the top, where the stem connects to the fruit. This shape is often described as being similar to a light bulb or teardrop. The skin of a pear can be smooth or slightly grainy, with colors ranging from green to yellow to brown.<br><br>In order to create visual representations of apples and pears or distinguish between them visually, you would need a different AI model specifically trained on images, such as a convolutional neural network (CNN). These models can process and generate images, enabling them to recognize and create visual representations of objects like apples and pears.<br><br><br></div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Fri, Apr 14, 2023 at 2:46 PM Gordon Swobe <<a href="mailto:gordon.swobe@gmail.com">gordon.swobe@gmail.com</a>> wrote:<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><br></div><div dir="auto">I’ll bet if you ask it to draw a perfect circle, it will draw one without ever having “seen” one. It should have learned from the language about circles including the language of mathematics of circles how to draw one. Is that really so amazing?</div><div dir="auto"><br></div><div dir="auto">-gts</div><div dir="auto"><br></div><div dir="auto"><br></div><div dir="auto"><div class="gmail_quote" dir="auto"><div dir="ltr" class="gmail_attr">On Fri, Apr 14, 2023 at 2:17 PM Gordon Swobe <<a href="mailto:gordon.swobe@gmail.com" target="_blank">gordon.swobe@gmail.com</a>> wrote:<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><br></div><div><br><div class="gmail_quote"><div dir="ltr" class="gmail_attr">On Fri, Apr 14, 2023 at 1:54 PM Giovanni Santostasi <<a href="mailto:gsantostasi@gmail.com" target="_blank">gsantostasi@gmail.com</a>> wrote:<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="ltr"><br>I showed you the different pics GPT-4 can create given nonvisual training. How can it draw an apple and know how to distinguish it from a pear…</div></blockquote><blockquote class="gmail_quote" style="margin:0px 0px 0px 0.8ex;border-left:1px solid rgb(204,204,204);padding-left:1ex"><div dir="ltr">These tasks have nothing to do with the statistical properties of words given they are spatial tasks and go beyond verbal communication. How do you explain all this? </div></blockquote><div dir="auto"><br></div><div dir="auto"><br></div><div dir="auto">They *do* have to do with the statistical properties of words and symbols and the relations and patterns between them. The shapes of pears and apples (and eyes etc) are describable and distinguishable in the language of mathematics.</div><div dir="auto"><br></div><div dir="auto">I agree it is amazing, but the “meaning” is something we assign to the output.</div><div dir="auto"><br></div><div dir="auto">-gts</div></div></div>
</blockquote></div></div>
</blockquote></div>