-14 points

I’ve been experimenting on creative writing tools with a bunch of writer friends, and the setup described in this paper is notoriously shit. I mean they come up to ChatGPT on v3.5 (or Bard lmao) and expect it to write comedy ? Jeez talk about setting yourself up for failure. That’s like walking up to a junior screenwriter and yelling “GIVE ME A JOKE” to them. I don’t understand why people keep repeating that mistake, they design experiments where they expect the model to be the source of creativity but that’s just stupid.

If you want to get output that is not entirely mediocre, you need something like a Dramatron architecture where you decouple various task (fleshing out characters, outlining at the episode level, outlining at the scene level, writing dialogues etc…) and maintain internal memory of what is being worked on. It is non-trivial to setup but it gets there sometimes - even the authors of this paper recognize that this would have probably produced better results. You also need a user able to provide good ideas that the model can work with, you can’t expect the good creative stuff to come from the robot.

Instinctively i’d say you have to treat the model like your own junior writer, and how do you make a junior writer useful ? By teaching them to “yes, and” in a writing room with better writers (in this case, the user). In that context, with a good experienced user at the helm, it can definitely bring value. Nothing groundbreaking but i can see how a refined version of this could help, notably with consistency, story beats, pacing, the boring stuff. GPTs are better critics than they are writers anyway.

That being said i never really pursued “pure comedy” on LLMs as it sounds like a lost battle. In my mind it’s kind of like tickling : if a machine pokes your ribs you don’t get the tickles, that only works when a human does it. I doubt they can fix that in the short or mid term.

permalink
report
reply
12 points

Hey, want some comedy advice? Read the room.

permalink
report
parent
reply
15 points

I want to point out that this interminable motherfucker introduced themselves as someone who supposedly does creative writing

permalink
report
parent
reply
15 points

I don’t understand why you’re getting downvoted. You should read the room, delete your posts, and leave forever. Then you wouldn’t be getting downvoted.

permalink
report
parent
reply
-11 points

Am i getting downvoted ? It says 3 upvotes / 0 downvotes on my end.

permalink
report
parent
reply
11 points

Here, have another invisible downvote.

permalink
report
parent
reply
13 points

I like how you lose faith in your argument the longer your post goes on. Maybe start with the last sentence next time.

permalink
report
parent
reply
-10 points
*

No i’m saying comedy (as in writing your jokes for you) is not something you should expect from language models. As a general rule, there is no tool that will make you a good writer, only (potentially) tools that can help you do more with your qualities as a writer. But it will never be funnier or more talented than you are.

That’s why i personally experiment with writing tools. Writing standup is one thing, but imagine you’re writing a sitcom or any form of serialized work. That’s a lot of fucking work and obviously if you’re starting out you can’t exactly afford to pay for assistant writers to do the menial labour that comes with it. Language models can come in handy in that scenario, but again you can’t expect them to be the genius in the room if you want a good show you have to bring the good ideas and the funnies. It’s a power tool and power tools don’t draw the plans for the house they just grind where you need grinding.

permalink
report
parent
reply
13 points
*

That’s a lot of fucking work and obviously if you’re starting out you can’t exactly afford to pay for assistant writers to do the menial labour that comes with it.

Give this promptfucker the props they deserve: usually they don’t just come out and say it.

permalink
report
parent
reply
12 points

comment history also includes simulation hypothesis and some very eagleflavoured political analysis

I have a prediction!

permalink
report
parent
reply
-4 points

What’s “eagleflavoured” ?

permalink
report
parent
reply
12 points

That’s a lot of words to say, “You’re holding it wrong.”

permalink
report
parent
reply
-7 points

More like “you’re trying to paint with a hammer AND you’re holding it wrong”

permalink
report
parent
reply
10 points

I mean they come up to ChatGPT on v3.5 (or Bard lmao) and expect it to write comedy?

Yeah, these things are supposed to be good at writing, aren’t they?

permalink
report
parent
reply
-7 points

Define “good at writing”. Good comedy is very difficult to attain and none of the models are anywhere near it, including the more recent ones.

permalink
report
parent
reply
13 points

Define “good at writing”.

I don’t want to.

Good comedy is very difficult to attain and none of the models are anywhere near it, including the more recent ones.

I concur.

permalink
report
parent
reply
23 points

Spam machines are only ever funny or interesting by accident. The more they smooth out the wrinkles the more creatively useless they become. The tension is sort of fascinating.

Like I’ve always been interested in generative poetry and other manglings of text, and ChatGPT’s so fucking dull compared to putting a sentence through babelfish a few times.

permalink
report
reply
6 points

Honestly, I’ve gotten more laughs out of messing with markov chains with my friends than anything ChatGPT could put out

permalink
report
parent
reply
6 points

GPT-2 was fun, because it was broken enough to be interesting and amusing.

permalink
report
parent
reply
5 points
*

Before the big AI boom, I actually did a project where I used inferkit to generate text for the comedy factor because the unhinged nightmare garbage it spit out was extremely entertaining. I just can’t imagine using chat gpt in the same way, it’s so boring

permalink
report
parent
reply
5 points

He come out, Stu.

permalink
report
reply
18 points

I can imagine a comedian using an LLM to check if a joke or punchline has been done before, but that would require the LLM to actually work and give accurate information. Also if you are a comedian using an LLM, you probably don’t actually care about whether or not you are plagiarising someone, so I guess this is all moot.

permalink
report
reply
15 points
*

My favorite LLM move is when you ask for a source for their last response, and instead of saying they aren’t capable of providing them, they just invent fictitious URLs.

permalink
report
parent
reply
21 points

oh, and these twenty comedians were using LLMs for writing already. They didn’t want their names revealed, for some reason.

permalink
report
reply
17 points

The adverse impacts section was just the comedians saying “we’ve already lost friends, everyone hates us” but the conclusion was “here’s how comedians should use our tool.”

permalink
report
parent
reply

TechTakes

!techtakes@awful.systems

Create post

Big brain tech dude got yet another clueless take over at HackerNews etc? Here’s the place to vent. Orange site, VC foolishness, all welcome.

This is not debate club. Unless it’s amusing debate.

For actually-good tech, you want our NotAwfulTech community

Community stats

  • 2K

    Monthly active users

  • 432

    Posts

  • 9.6K

    Comments

Community moderators