Hacker News new | past | comments | ask | show | jobs | submit login

I'd like to explore more the fan-out pattern:

- having it generate an outline

- have multiple clones write each section of the outline

- a stage which synthesizes the parallel-written sections, capturing the best

- a stage which combines all sections and ensures flow based on the original outline

- finally a stage which critiques and generates edits.

Iterate a couple times and you might actually have something good!

Basically a lot of what this article does, but automated.




As a reader, would you ever prefer to be given the AI-fluffed version instead of the outline? I say if you have a few concise bullet points of the point you want to get across fantastic, let me read them and be on my way.

If on the other hand your mission is to produce a proper creative writing work where the choice of words is the art, then if you don't do that yourself what's the point?


This is something I've wondered for a while too. Like Notion's AI has a "make longer" button.... why would I ever want AI to arbitrarily fluff something up adding extra words unless I was a kid writing an exam and needed 3 more pages? I can't find any legitimate use for that feature.

EDIT: In case it's not clear, No. I would rather read the shortest version possible than one fluffed up by AI to make a word count. As far as creative stuff goes, I'm not sure that I've seen a situation where AI made something interesting enough that I'd want to read extra words from it.


> As a reader, would you ever prefer to be given the AI-fluffed version instead of the outline?

Why read Huckleberry Finn when you can read the cliffs notes?

Summarization is lossy, usually on the experiencing part.


But having AI extend your notes includes all the loss of the initial summarization, with extra AI randomness on top. It can't recover the information lost in the summary, that's what makes the summary lossy.


It can, in the way you can follow the abstract of a paper with its body. Don't forget that the model has access to the original text; it's not just going off the summary.


See second paragraph.


> Why read Huckleberry Finn when you can read the cliffs notes?

The difference should be self-evident.


I used to publish a TLDR at the top of some of my blog posts because I’m so verbose!


How do you prompt something like that?

At least for 7B and 13B models I've found they give the initial outline and then stop following the instructions.


you'd have to do a chain of prompts with specific instructions for the input from the previous step to have a chance of it working


We do use similar flow in Surfer AI and confirm it actually works wonders.




Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: