https://www.wizardemporium.com/blog/complete-list-of-harry-p...
Why is this impressive?
Do you think it's actually ingesting the books and only using those as a reference? Is that how LLMs work at all? It seems more likely it's predicting these spell names from all the other references it has found on the internet, including lists of spells.
No need for surprises! It is publicly known that the corpus of 'shadow libraries' such as Library Genesis and Anna's Archive were specifically and manually requested by at least NVIDIA for their training data [1], used by Google in their training [2], downloaded by Meta employees [3] etc.
[1] https://news.ycombinator.com/item?id=46572846
[2] https://www.theguardian.com/technology/2023/apr/20/fresh-con...
[3] https://www.theverge.com/2023/7/9/23788741/sarah-silverman-o...
"Researchers Extract Nearly Entire Harry Potter Book From Commercial LLMs"
https://www.aitechsuite.com/ai-news/ai-shock-researchers-ext...
This definitely raises an interesting question. It seems like a good chunk of popular literature (especially from the 2000s) exists online in big HTML files. Immediately to mind was House of Leaves, Infinite Jest, Harry Potter, basically any Stephen King book - they've all been posted at some point.
Do LLMS have a good way of inferring where knowledge from the context begins and knowledge from the training data ends?
Anna's Archive alone claims to currently publicly host 61,654,285 books, more than 1PB in total.
https://www.washingtonpost.com/technology/2026/01/27/anthrop...
Anthropic, specifically, ingested libraries of books by scanning and then disposing of them.
The plot of Good Will Hunting would like a word.
If you ask a model to discuss an obscure work it'll have no clue what it's about.
This is very different than asking about Harry Potter.
There are many academic domains where the research portion of a PhD is essentially what the model just did. For example, PhD students in some of the humanities will spend years combing ancient sources for specific combinations of prepositions and objects, only to write a paper showing that the previous scholars were wrong (and that a particular preposition has examples of being used with people rather than places).
This sort of experiment shows that Opus would be good at that. I'm assuming it's trivial for the OP to extend their experiment to determine how many times "wingardium leviosa" was used on an object rather than a person.
(It's worth noting that other models are decent at this, and you would need to find a way to benchmark between them.)
In your example, it might be the case that the model simply spits out consensus view, rather than actually finding/constructing this information on his own.
The poster knows all of that, this is plain marketing.
Do you have a citation for this?
