![]() The difference is really whether you want to prove an AI can’t do something, or instead treat it like a mutual teaching interaction, as though you were teaching to a bright student with specific disabilities. You can aid the AI in figuring out the correct solution, and I find it fascinating that this is possible, that you can watch them learn through the conversation. With a lot of scenarios where people say ChatGPT failed, I have found that their prompts as is did not work, but if you explain things gently and step by step, they can do it. I find it all the more impressive that what they generate is not meaningless, and improves. ChatGPT learned language first, not math, they struggle to do things like accurately count characters. It is clearly something tricky for them, though. We need to explain ASCII like you are explaining it to someone who is blind and feeling along a set of equally spaced beads, telling them to arrange the beads in a 3D construct in their heads. And notably, ChatGPT learned across the conversation and improved, despite the fact that I was stuck by how humans were giving an explanation that is terrible if the person you are explaining things to cannot see your interface. ![]() I’ve seen attempts to not just request ASCII, but teach it. ![]() I’ve been meaning to do that, see if I can teach them spatial reasoning that way, save the convo and report it to the developers for training data, but was unsure if that was a good way for them to retain the information, or whether it would become superfluous as image recognition is incoming. This would enable them to learn the spatial relations between the numbers, first in 2D, then in 3D. And you tell them that if there is a row of characters 8 characters long, this means the ninth character will be right under the first character, the tenth right under the second, etc. This changes if we only use characters of equal width, and a square frame. With a bunch of the pics they produce, you notice they are basically off in the way you would expect if you didn’t know the width of individual characters. That entails so much information that is simply missing for them. Basically, if you were given an ASCII art in a string, but had no idea how the individual characters looked or what width they had, you would have no way to interpret the image.ĪSCII works because we perceive characters both in their visual shape, and in their encoded meaning, and we also see them depicting in a particular font with particular kerning settings. I think ASCII art in its general form is an unfair setup, though ChatGPT has no way of knowing the spacing or width of individual letters, that is not how they perceive them, and hence, they have no way of seeing which letters are above each other. This loss can affect the model’s ability to produce well-aligned ASCII art.įor this very reason, I was intrigued by the possibility of teaching them vision this way. Loss of formatting during preprocessing: When text is preprocessed and tokenized before being fed into the model, some formatting information (like whitespaces) might be lost or altered. This inconsistency makes it difficult for the model to learn a single, coherent way of generating well-aligned ASCII art. As a result, it struggles to maintain the correct alignment of characters in ASCII art, where spatial organization is essential.įormatting inconsistencies in training data: The training data for GPT-4 contains a vast range of text from the internet, which includes various formatting styles and inconsistent examples of ASCII art. Lack of spatial awareness: GPT-4 doesn’t have a built-in understanding of spatial relationships or 2D layouts, as it is designed to process text linearly. In case there is any doubt, here is GPT4′s own explanation of these phenomena: But given that it has been trained on a lot of ASCII art, it will probably be successful at copying some of it some of the time. ChatGPT really doesn’t see lines arranged vertically, it just sees the prompt as one long line. I think it makes sense that it fails in this way. ![]() Then I asked if it could do the Vitruvian Man as Ascii art, and it said: O
0 Comments
Leave a Reply. |
AuthorWrite something about yourself. No need to be fancy, just an overview. ArchivesCategories |