NotebookLM as an authoring system

Some folks here might find this amusing (or just clumsy)…

Complete Sherlock Holmes & Game
https://notebooklm.google.com/notebook/2c4f0f26-0797-4cc0-a350-48c4b70d14cc

I tried playing, but the “game” was very much on rails and pretty much steered me to my “Brilliant deduction”. Interesting idea though–use an LLM to explore an existing work of fiction with an IF interface.

1 Like

ok, I couldn’t resist giving it a try:

The Pride & Prejudice Virtual World

Here’s a transcript of that.

It can pull off some nifty mimesis carried through the medium term, like when I had the protagonist fold the letter into a paper crane, then went inside and had her meditate and sleep before undoing the origami to read it.

1 Like

Great transcript. LOL moments:

State: Armed with the secret of Mr. Bennet’s visit to Netherfield, but choosing to hug sisters instead.

You decide that the absolute best use for a heavily-sealed, hot-pressed letter from a gentleman of ten thousand a year is to subject it to the ancient art of origami.

SLEEP AND DREAM LUCIDLY

Slipping into a delightfully lucid dream, you find yourself wandering the familiar gravel walks of Longbourn. The handsome Mr. Wickham approaches, looking as universally admired as ever in his regimentals. Yet, as you exert your lucid control to demand a display of his substantial virtues, his charming facade begins to waver. He smiles with his usual engaging ease, but instead of offering amiable conversation, he cheerfully asks if you might lend him a thousand pounds to settle his pressing debts of honour! Before you can deliver a scathing reply, a flock of crisp, ten-thousand-a-year paper cranes descends from the sky, chasing the distressed officer away into the shrubbery.

1 Like

While reading the transcript, I thought, oh that’s interesting, @Bainespal tried to GO TO MR BINGLEY’S HOUSE. What’s going to happen?

I don’t read a lot of transcripts, but I read this one eagerly. This got me thinking, why?

Context for the opinion that’s about to follow: I enjoy simple meaningful puzzles, but don’t like ones that are so hard that you have to go consult InvisiClues, and I like it more when the game stands on a literary ambition. I’m an All Roads fan.

So why read a transcript? On one end of the spectrum: just show me how to solve the damn puzzle so I can move on. The other end: please print this in book form so I can showcase this author’s flawless writing on my coffee table.

The LLM interaction is interesting, because the LLM is like a game master and the player has some agency in shaping the narrative in a creative way. The outcome is that the transcript is something the player helps shape.

This is a new dynamic to me that breaks the spectrum. The player is now part of the creative process. Reading someone else’s transcript becomes more intriguing: 1) how did their narrative unfolded as compared to mine? and 2) what creative things they did they do and how did the LLM game master incorporate those idiosyncracies and keep the game from going off the rails? (or maybe the game does go off the rails in some way that is also thought provoking).

Then new dynamic: The transcript is interesting because I played the game too, as opposed to not being interesting because I already played it.

1 Like

Good insights–the transcript as an artifact is inherently different in any LLM chat than a transcript as a session of gameplay.

That’s why this is not weird sloppy IF with a super flexible parser; it’s another genre, albeit related. Hypertext fiction as originally imagined were always different too, because they had a different relationship between the narrative and the player – not necessarily talking about Twine games here, which are often highly influenced by parser IF and have player representation.

LLM fiction is a new genre in the family, related most closely to certain kinds of narrative TTRPGs and to parser IF. I think mainstream efforts in this space like AI Dungeon already belong to this genre, as well as paste-in context games as are often seen outside of the IF Community but have shown up in the Comp. I think the avatar roleplayers, who have communities on Reddit, for example, are not really part of the same genre, even though they also use LLMs and are also at least somewhat related.

I think there will always be overlap and games that legitimately qualify as both IF and LLM fiction for both historical reasons and for really legitimate categorical ambiguity and relevance – this is the same case, imo, as with the classic hypertext fiction of Eastgate. Most of the Eastgate stories are not and in my opinion never were IF, in my opinion; historically their community was also thought of as distinct despite relevance. But some of the Eastgate games might be listed with IF due to historically connections, and others of them (i.e., King of Space – I recently played its reconstruction) are pretty definitively also IF (or whatever genre most Twine games are), because they model the player, have some mechanics, and don’t dissociate the traversal of the narrative from the interactivity in the same way as pure hypertext fiction.

I’m beginning to see a similar dynamic emerging between parser IF and LLM fiction. There is huge mutual relevance, historic models that overlap. This is not simply the case of LLM fiction ripping of – hallucinating – the structure of IF gameplay based on training data. It’s also the case that historic IF was always informed by early concepts of Turing-test-passing chatbots. (Yeah, to be sure, most of the similarity is indeed due to LLMs simply simulating IF. But that doesn’t have to be an inherent feature of the LLM fiction genre. There are other subtypes of LLM fiction; some of them are more TTRPG like, some of them are reminiscent of old forum roleplaying or simple web-based MMOs.)

I think the LLM fiction space should get a community to help it emerge as distinct from IF. This will be good for both genres and for everyone involved. I want to like both genres. I’m really excited about the emergence of LLM fiction; I think it delivers a lot of what I thought had been some of the suggestions inherent in parser IF. On the other hand, I don’t want to forsake traditional parser IF due to the existence of LLMs anymore than I would have forsaken it because of graphical games. This way, the IF community can remain mostly free of most LLM-based noise. And hopefully this would allow someone who sometimes uses AI to participate in IF community events without suspicion of brining in LLM use and LLM prejudice into the picture, because it would be understood that the LLM stuff is mostly a separate scene and someone can do both in their respective places.

We should start documenting existing LLM fiction titles and make a forum.