Hacker News new | ask | show | jobs
by Der_Einzige 1128 days ago
A lot of this is because there was and still is systemic undertooling in NLP around how to prompt and leverage the wonderful LLMs that they built.

We have to let the Stable Diffusion community guide us, as the waifu generating crowd seems to be quite good at learning how to prompt models. I wrote a snarky github gist about this - https://gist.github.com/Hellisotherpeople/45c619ee22aac6865c...