They/the LLM made sure to replace the em dashes with semicolons

jaggederest an hour ago | parent | next [-]

This is a fun challenge, I think: make the AI generate text with no obvious AI shibboleths. I haven't found a good way to do it at all yet, the more you ask it not to, the more you lower the output quality, which paradoxically makes it more sloppy, not less. Funnily enough I think "lower-power" LLMs are much better at this, like Haiku is much better at keeping voice on track with those kinds of instructions.

	▲	AndyNemmity 39 minutes ago \| parent [-]
		I have done it for a long time now. It's actually pretty straight forward to do it, but you have to run it in a pipeline, and you have to add deterministic checks as well. There was an odd key to unlocking it sounding like a human. I spent like a month on this topic last year, and I randomly stumbled upon something that ended up massively improving generated tests. It was a shot in the dark after failing so often. And then it suddenly sounded good.

▲

mmooss 19 minutes ago | parent | prev [-]

Sometimes you can use a semicolon where you use an em dash, but that's only coincidence: They serve different functions and usually you can't.

Rae bought all the candy at the store - Milky Way, Reese's, M&Ms, everything - and set out for Kay's party.

That can't be rewritten as,

Rae bought all the candy at the store; Milky Way, Reese's, M&Ms, everything; and set out for Kay's party.

Semicolons set off independent clauses - what would otherwise be complete sentences. Em dashes create breaks in the flow of the sentence; commas are more similar.