These hallucinations are compression artifacts, but-like the incorrect labels generated by the Xerox photocopier-they are plausible enough that identifying them requires comparing them against the originals, which in this case means either the Web or our own knowledge of the world. It's also a way to understand the "hallucinations," or nonsensical answers to factual questions, to which large-language models such as ChatGPT are all too prone. This analogy to lossy compression is not just a way to understand ChatGPT's facility at repackaging information found on the Web by using different words. You're still looking at a blurry JPEG, but the blurriness occurs in a way that doesn't make the picture as a whole look less sharp. But, because the approximation is presented in the form of grammatical text, which ChatGPT excels at creating, it's usually acceptable. It retains much of the information on the Web, in the same way that a JPEG retains much of the information of a higher-resolution image, but, if you're looking for an exact sequence of bits, you won't find it all you will ever get is an approximation. Think of ChatGPT as a blurry JPEG of all the text on the Web. What I've described sounds a lot like ChatGPT, or most any other large-language model. It turned out that the photocopier had judged the labels specifying the area of the rooms to be similar enough that it needed to store only one of them-14.13-and it reused that one for all three rooms when printing the floor plan. To save space, the copier identifies similar-looking regions in the image and stores a single copy for all of them when the file is decompressed, it uses that copy repeatedly to reconstruct the image. Xerox photocopiers use a lossy compression format known as JBIG2, designed for use with black-and-white images. Combine that with the fact that virtually every digital image file is compressed to save space, and a solution to the mystery begins to suggest itself. Instead, it scans the document digitally, and then prints the resulting image file. They needed a computer scientist because a modern Xerox photocopier doesn't use the physical xerographic process popularized in the nineteen-sixties. The company contacted the computer scientist David Kriesel to investigate this seemingly inconceivable result.
However, in the photocopy, all three rooms were labelled as being 14.13 square metres in size. In the original floor plan, each of the house's three rooms was accompanied by a rectangle specifying its area: the rooms were 14.13, 21.11, and 17.42 square metres, respectively. In 2013, workers at a German construction company noticed something odd about their Xerox photocopier: when they made a copy of the floor plan of a house, the copy differed from the original in a subtle but significant way.
0 kommentar(er)
