pull down to refresh

156 sats \ 3 replies \ @SimpleStacker 28 Jan \ parent \ on: Best small and open instruct models? AI AskSN devs

Can't help it if AI was trained on the way people like me write 🤷🏻‍♂️

write
preview
0 sats \ 2 replies \ @k00b OP 28 Jan

You read so model like sometimes it trips me out. Someday we'll be able to look into the models and see all the SimpleStacker weights.

reply
0 sats \ 1 reply \ @SimpleStacker 28 Jan

Looking back at that specific phrase, it's indeed very botlike

reply
0 sats \ 0 replies \ @k00b OP 28 Jan

It does sound like a model orienting itself for a reply.

(I tend to draw pretty heavily on this finding from image diffusion models to understand how LLMs build coherent output. I'm probably overgeneralizing it.)

reply