Live data from Hacker News

Show HN: Graph-based AI for longform writing

jotte.ai

41–50 of 81 posts

Re: Show HN: Graph-based AI for longform writing

#41

Earlier quoted context omitted.

E.g. you can imagine implementing an AI D&D dungeon master this way. It could even trigger things like (AI-synthesized) music at the right time. Or you could build an AI girlfriend/conversation partner.

I don't understand exactly how that would work. At some point, the generation would introduce new events and characters, new places or objects, and name them, but then when summarising, won't the names of some of them be lost, just because there's not enough space in the summary to name them all? The same goes for all sorts of detail, not necessarily named. At that point, what happens to the narrative about those for…

I think once we have an LLM that can take books 6-12 of the Wheel of Time saga and turn them into a single book we'll be close enough for the size of the memory not to matter.

Re: Show HN: Graph-based AI for longform writing

#42

What exactly is the use case for "longform writing by AI"? Profiting from mass-produced zero-effort novels?

I work in biology and plopping DNA into GPT-style models kind of works, but there are many long-distance interactions within genomes that are more distant than current GPTs can encode. In some plants there's linkage (~gets inherited together more often than expected) across tens of thousands of base-pairs (~letters), so having these long-distance models will be very useful!

Re: Show HN: Graph-based AI for longform writing

#45
Very interesting! I'm giving it a try now, a few thoughts:

1. The default "Node 1" etc titles on cards is unfortunate. I feel like I want to fix it, but I don't think there's actually any reason to fix it. Generated passage/subsection titles would be nice.

2. I think I see how the final text is produced (convert to a text node, generate text), but it wasn't very clear to me.

3. "Events" isn't that clear to me. Should I just add details I like to that? Or focus on plot? Do I actually write final text here?

4. I hope your budget is OK! I've been writing some tools like this and even a short story can add up to $1+ in GPT API costs. (Though maybe I'm being too generous in my GPT prompts/responses.)

4b. Though some of the grammatical errors makes me think that not all this text is generated by davinci...?

4c. This really went off the rails... I gave the text "Jane met Joe on Tinder. Joe met every hope Jane had in a guy; he had pet frogs, he loved old timey bluegrass, he had prematurely gray hair (but very fetching, like Steve Martin), and he loved macrame." and it generated "The first date went well. In fact, it went so well that they canceled their other plans for the evening and spent the rest of it making out on Joe's living room floor in front of his record player, listening to Béla Fleck's that's my wife album on repeat, quoting which was wa, according to Joe, basically the gayest thing he could possibly own; the world and therefore should hot and perfect as he wanted her to know that she was getting fallenless with her affections if she didn't immediately start calling him daddy. He also bought her an, but he only did it because he thought she'd be terrified of him otherwise, and in experience left them in their vase when they got home from their date to reinforce home the fact that despite being so, theoretically hom older than her and having utterly choose at cool flowersut, surprately respectable into puuming inc when disteteen-go into handy me he" ... that's a lot of not-words!

5. I got confused about focus and how the Summarize/etc buttons appear. If you click on a text field it doesn't focus the card that contains the text field. I spent a somewhat embarrassing amount of time looking for those buttons after I made my first card :)

6. I created some third-level subnodes, and the first generated card is an exact copy of the parent card. I would have expected it to just be the first part of it.

7. Though I realize it's not clear to me how any of that is supposed to work. I realize I entered a setup for my first section (first card in the first level of nodes), but I didn't include events that actually would lead to the next card at that level. GPT kind of filled that in, and so maybe that copied card was appropriate.

8. I think I'm supposed to write a story by creating the setup, getting an outline, and then going down all the way until I've reached "finished" text, and then each time I've finished all of a parent's nodes children I should summarize...? Do I just not summarize leaf nodes?

9. Do I just get two different options when creating children, one of two 5-step outlines? Sometimes neither is what I want. 5 also feels like it's too many at some levels.

10. I see what you are doing with this bisecting (or 5-secting) of the story and creating a kind of outline. But this still means very big jumps. Like if I go down 3 levels then there's actually a lot of distance between those leaf nodes when adjacent parts of the story belong to different top-level nodes.

11. Maybe a better approach would be a sliding window, where there's no "graph" but instead a kind of fractally-expanding linear flow, with an ever-blurrier summary as you get further from the area of the story being actively developed.

11b. I mention this because I'm getting continuity errors. Which is also just really hard to fix. But when I start at the beginning and I've started the outline, I've committed to the beginning getting to a particular next step (also I want it to get to that next step).

11c. In general I've noticed GPT really wants to advance the story too quickly. Like I had a passage about someone meeting a person on Tinder, and Jotte suggested outlines where that was broken down into events that led to them being married. The breakdown should still be strictly about meeting the person on Tinder (and then a bunch of character building detail... this isn't a news report). It's going to be hard to keep GPT from trying to "complete" the story when the whole concept is that it should only complete events described in the parent node, and leave what comes next to the next card.

11d. This feels like it's not going to be able to handle foreshadowing. Or at least I'm not seeing it. The person the main character meets on Tinder is secretly an alien catfishing for people to kidnap. The story shouldn't give that away, but the reader should feel like something is fishy.

11e. If I have ideas about the style of the story and exposition, where do I put them? Events? Will it respect these as notes to inform its composition, and not literal events in the story? Or is Theme where I put the meta-guidance? (I don't understand theme... it feels like it's suggestions for the voice of the writing, but that shouldn't shift as often as theme shifts.)

I'm also getting some exceptions, I copied them here: https://gist.github.com/ianb/42e8d906b1c2dfbd32e00dff907e612...

Re: Show HN: Graph-based AI for longform writing

#46
post #2

I am glad to see more stuff with graph based AI here. I have a running bet with a friend about whether future is going to be OBM (One Big Model) or LoLM (Lots of Little Models). I'm strongly in the LoLM/graph camp and have been working in that direction as well: https://github.com/Miserlou/Helix

Woah, seeing that github handle takes me back to 2015 when I was working in python and you had a tool to quickly bootstrap aws lambda services (zappa?).

Re: Show HN: Graph-based AI for longform writing

#47
post #2

I am glad to see more stuff with graph based AI here. I have a running bet with a friend about whether future is going to be OBM (One Big Model) or LoLM (Lots of Little Models). I'm strongly in the LoLM/graph camp and have been working in that direction as well: https://github.com/Miserlou/Helix

Very interesting! "The general hypothesis of the project is: Consciousness, or something resembling consciousness, emerges not from the capability of a single task model like GPT or Stable Diffusion, but from the oscillations between the inputs and outputs of different instances of different models performing different tasks."

Your metaphors of self-oscillation and multiple oscillations are very much in line with the consciousness model that is built on the top of Adaptive Resonance Theory. I believe this is the most computationally robust model for consciousness. You might want to read/skim this https://www.sciencedirect.com/science/article/pii/S089360801...

That can be a forbidding read because it packs so much (65 years of work!)

You can also read Journey of the Mind (https://www.goodreads.com/book/show/58085266-journey-of-the-... I'm the co-author) which, among other things, covers Grossberg's work and his model of consciousness built on the idea of resonance. Here resonance goes beyond the metaphorical idea and has a specific meaning.

edit: https://saigaddam.medium.com/understanding-consciousness-is-... (here's a super brief description of Adaptive Resonance Theory )

Re: Show HN: Graph-based AI for longform writing

#48

Earlier quoted context omitted.

I see zero problem with that. If great literary works can be produced with a click of a button we should do it. And if they’re not great then they’re not great - we’re already more than capable of producing not great novels.

> And if they’re not great then they’re not great You see no problem with flooding every market with junk products that cost nothing to produce so that non-junk products are crowded out and impossible to find? This is exactly the thing that everyone now hates Amazon for and why trying to find honest reviews of anything online is so horribly frustrating. Some barrier to entry is always better than no barrier to entry.

I found the Amazon Wheel of Time boring, as if it was produced by a machine or something. I assume it will be even worse once they start using AI for doing similar things.

Language-model AI can simulate texts, but it cannot simulate how reading such texts make humans feel. Only a human writer can do that and only that makes texts truly entertaining.

Re: Show HN: Graph-based AI for longform writing

#49

Earlier quoted context omitted.

I see zero problem with that. If great literary works can be produced with a click of a button we should do it. And if they’re not great then they’re not great - we’re already more than capable of producing not great novels.

If they're universally bad though, they will flood the world with crap and make it very difficult to find the great (i.e. human-written) literary works.

It might become a difference like with synthetic polyester fabrics and vs. wool and silk. Or organic food vs. processed food. People will pay more for the "real thing".

Re: Show HN: Graph-based AI for longform writing

#50

What exactly is the use case for "longform writing by AI"? Profiting from mass-produced zero-effort novels?

Fake investigative journalism "proving" whatever you want people to believe. Alternatively, a critical mass of such "journalism" convincingly arguing for contradicting theories, making people confused and apathetic on the topic of your choice.

I'm afraid that, no matter what the engineers' original intention, if it works well enough, this is what it'll be remembered for.

Post reply on HN