Using GPT-4 to measure the passage of time in fiction

Re:Using GPT-4 to measure the passage of time in fiction by gary_0 on Friday June 23, 2023 @07:31AM (#36445422)

I took that more to mean that most LLMs won't spontaneously produce new insights given a general topic ("a paper about Middlemarch" being the example given). Their default mode is just to barf out somewhat patronizing summaries or answer questions with dry facts (and occasional factual-sounding nonsense).

It takes coaxing (and some cherry-picking) to get anything creative out of LLMs -- and some people suspect newer versions are so locked-down to avoid sounding "scary" that they actively avoid saying anything too interesting or philosophical.

The line between "creative output" and "hallucinated madness" is also somewhat blurry (for humans and LLMs alike...)

[ Parent | on HN ]

Re:Using GPT-4 to measure the passage of time in fiction by logicchains on Friday June 23, 2023 @11:24AM (#36448133)

>It takes coaxing (and some cherry-picking) to get anything creative out of LLMs

I assume by LLMs you actually mean "ChatGPT and similar commercial LLM services". Raw LLMs like LLaMA and Falcon will happily spout out the craziest, sometimes super creative ideas, it's just the lobotomising of ChatGPT and the like that destroys their creativity.

[ Parent | on HN ]

Re:Using GPT-4 to measure the passage of time in fiction by SketchySeaBeast on Friday June 23, 2023 @12:18PM (#36448959)

Isn't a problem that the more creativity the more likely it'll also be nonsensical or off topic?

[ Parent | on HN ]

Re:Using GPT-4 to measure the passage of time in fiction by circuit10 on Friday June 23, 2023 @12:32PM (#36449166)

Well, it's a tradeoff, RLHF also makes ChatGPT better at some tasks like instruction following. "lobotomising" makes it sound like there are only downsides

[ Parent | on HN ]

Re:Using GPT-4 to measure the passage of time in fiction by majormajor on Friday June 23, 2023 @12:55PM (#36449452)

If you crank the temperature param up on GPT4 in the API you get madness very quickly, usually shortly after 1.4ish in my (albeit limited) testing.

Sadly it didn't seem to be a fun, usuable, creative madness to me (a la a human on certain drugs), but YMMV.

[ Parent | on HN ]

Re:Using GPT-4 to measure the passage of time in fiction by selalipop on Friday June 23, 2023 @01:11PM (#36449658)

I've gotten them to be creative in ways that were unexpected, like outputting tokens that have absolutely no (obvious) relation to the current conversation

While trying to iterate on a name for a product, I had it output an internal monologue alongside outputting name ideas.

With each iteration of naming I'd ask it to probe its understanding in of human creativity and list how the usefulness/realism of the internal monologue.

After a few loops the internal monologue started modeling fleeting memories about things like "that time at camp where X happened".

Eventually it was modeling fleeting thoughts like "the warmth of the cup of coffee on the desk" as a source of inspiration, and random observations like "it looks like traffic is picking up outside, getting to yoga will take a while" in the middle of a name generation task

—

I made a website predicated on a similar idea after that: https://notionsmith.ai

Technically it's a hallucination generator, but I think you described why I made it (creativity and hallucinations really are similar for both LLMs and humans)

[ Parent | on HN ]