TechTakes

1437 readers

84 users here now

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

founded 1 year ago

MODERATORS

[email protected]

126

Actual comedians try to use LLM in a writing room. Result: “cruise ship comedy material from the 1950s, but a bit less racist” (arxiv.org)

submitted 4 months ago by [email protected] to c/[email protected]

50 comments fedilink hide all child comments

you are viewing a single comment's thread
view the rest of the comments

[–] [email protected] 13 points 4 months ago

Dunno what you want me to say. Define the vague concept of "good writing"?

The linked study finds that ChatGPT 3.5 and Bard suck at writing comedy. You claim in so many words that this should be obvious (along with a really dubious claim that machines can't tickle people for some reason). I'm also not surprised that these models are terrible at writing comedy, because even at best of times I find their output bland, trite and crudely stripped of anything potentially divisive.

However, lots of people seem to think that LLMs are good at writing related tasks, so I don't think it's inherently obvious that these tools suck at writing comedy in particular.

All these words make this reply much less fun to write.