@sqgl@beehaw.org to Jokes and Humor@beehaw.org • 2 months agoBe nice to Googe and Siribeehaw.orgimagemessage-square10fedilinkarrow-up1172
arrow-up1172imageBe nice to Googe and Siribeehaw.org@sqgl@beehaw.org to Jokes and Humor@beehaw.org • 2 months agomessage-square10fedilink
minus-square@itslilithlink20•2 months agoThere was a paper about that actually, results get better when asked politely That’s because high-quality sources usually use formal and/or polite language, so priming the model with this sort of input enhances output Also, it’s just nice
There was a paper about that actually, results get better when asked politely
That’s because high-quality sources usually use formal and/or polite language, so priming the model with this sort of input enhances output
Also, it’s just nice