Google search hallucinates Encanto 2. Jason Schreier on Bluesky:
I was excited to tell my kids that there's a sequel to Encanto, only to scroll down and learn that Google's AI just completely made this up
I just replicated the same result by searching Google for encanto 2. Here's what the "AI overview" at the top of the page looked like:
Only when I clicked the "Show more" link did it become clear what had happened:
The link in that first snippet was to the Encanto 2: A New Generation page on Idea Wiki:
This is a fanon wiki, and just like fan-fiction wikis, this one has a variety of fan created ideas on here! These include potential sequels and new series that have yet to exist.
Other cited links included this article about Instagram fan art and Encanto's Sequel Chances Addressed by Disney Director, a very thin article built around a short quote from Encanto's director at D23 Brazil.
And that August 2024 release date (which the AI summary weirdly lists as "scheduled for release" despite that date being five months in the past)? It's from the Idea Wiki imaginary info box for the film.
This is a particularly clear example of how badly wrong AI summarization can go. LLMs are gullible: they believe what you tell them, and the web is full of misleading information - some of which is completely innocent.
Update: I've had some pushback over my use of the term "hallucination" here, on the basis that the LLM itself is doing what it's meant to: summarizing the RAG content that has been provided to it by the host system.
That's fair: this is not a classic LLM hallucination, where the LLM produces incorrect data purely from knowledge partially encoded in its weights.
I classify this as a bug in Google's larger LLM-powered AI overview system. That system should be able to take the existence of invalid data sources into account - given how common searches for non-existent movie sequels (or TV seasons) are, I would hope that AI overviews could classify such searches and take extra steps to avoid serving misleading answers.
So think this is a "hallucination" bug in the AI overview system itself: it's making statements about the world that are not true.
Recent articles
- My AI/LLM predictions for the next 1, 3 and 6 years, for Oxide and Friends - 10th January 2025
- Weeknotes: Starting 2025 a little slow - 4th January 2025
- I still don't think companies serve you ads based on spying through your microphone - 2nd January 2025