# Citation glitch being perpetually reiterated by AI **URL:** \ **Category:** Miscellaneous and Personal Stuff I Must Share\ **Created:** [April 16, 2025, 5:45pm UTC](https://boards.straightdope.com/t/citation-glitch-being-perpetually-reiterated-by-ai/1017111 "2025-04-16T17:45:17Z")\ **Posts on this page:** 1\ **Showing post:** 15
**Author:** ![Reply](https://sea3.discourse-cdn.com/straightdope/user_avatar/boards.straightdope.com/reply/32/15952_2.png) [@Reply](https://boards.straightdope.com/u/Reply)\ **Post date:** [April 16, 2025, 9:47pm UTC](https://boards.straightdope.com/t/citation-glitch-being-perpetually-reiterated-by-ai/1017111/15 "2025-04-16T21:47:51Z")
Somewhat ironically, ChatGPT is actually pretty good at explaining how it itself works: [How LLMs work, explained in 3 _Lord of the Rings_ haikus by ChatGPT](https://chatgpt.com/share/68002553-0930-8011-859e-38331987b3cf) In that chat, I asked it to explain how LLMs work, and clarified with several follow-ups. Then I asked it to use a special mode, read a bunch of scholarly papers, and then analyze them vs its earlier explanations to summarize the major points with citations. It [continually re-prompted itself in a “chain of thought”](https://share.cleanshot.com/GQYfHk8fZp8QJfYQcRtw) to read different sources and add them to its context. Then I asked about it hallucinations. This conversation helped me understand how we go from “token prediction like your phone’s autocomplete” to “how is it able to actually understand a prompt, break down its question into tokens, and extract sufficient meaning in order to answer it”. Of course, the sad thing is… I don’t know if that convo was entirely hallucinated. It seemed plausible enough, and the terms seem to check out, but we’re quickly veering towards an all-AI reality bubble where it’s impossible to verify anything anymore… 🤷 * * * If you prefer human responses, we also recently had a similar thread about this, with a lot of discussion and additional info: [chatGPT is a fucking liar](https://boards.straightdope.com/t/chatgpt-is-a-fucking-liar/1016559) There were [some explainer videos in post #38](https://boards.straightdope.com/t/chatgpt-is-a-fucking-liar/1016559/38). Those visualizations are helpful for seeing a (simplified) representation of the token prediction process, especially at [3:03 in this “Transformers (how LLMs work) explained visually” video](https://youtu.be/wjZofJX0v4M?si=OBl_RdIARxHjuqrT&t=183). That’s part of a whole series and several talks (by what seems to be a person). Who can tell anymore… --- _[View the full topic](https://boards.straightdope.com/t/citation-glitch-being-perpetually-reiterated-by-ai/1017111)._