"While ChatGPT has become a global meme," writes Donald Clark, "it actually distracts from the many other uses of AI for learning." In particular, he says, we should be paying attention to semantic search. "At the moment search is keyword driven and often misfires," he says. "Traditional search matches exact targets, not a range of similar or related targets, so you get lots of misfires (but) when you turn language into mathematical vectors in a transformer, you capture a word or sentence's relationship to other word." Semantic search, in other words, is based on the meaning of the search term, and not the physical characteristics of the search term. Perplexity.ai offers an example of how AI may be redefining search; instead of looking for words, you ask it a question, and it consults a wealth of internet resources to find you an answer. But there's still a long way to go, as Barry Dahl discovers when he tries a few such systems to describe the history of D2L, and mayhem ensues.
Today: 1 Total: 12 [Direct link] [Share]
