I know this is not the theme of this post, but I wonder if there’s an LLM that doesn’t hallucinate when asked to summarize information of a group of documents. I tried Gpt4all for simple queries like finding out which documents mentioned a certain phrase. It often gave me filenames that didn’t actually exist. Hallucinating contents is one thing but making up data source is just horrible.
Perhaps the reason is more simple. When did we have a non-indie platformer title well received by the mass? I don’t think people want a combo of “platformer” and “AAA” (hence the price).