Finding signal on Twitter is more difficult than it used to be. We curate the best tweets on topics like AI, startups, and product development every weekday so you can focus on what matters.
5.6 and fable seem markedly better at writing prompts. | Tech Twitter
Press Space to continue
5.6 and fable seem markedly better at writing prompts.
historically, models have been very bad at writing prompts.
it makes sense - historically training data don't contain a lot of good prompt data for obvious reasons.
there should be a benchmark for prompt writing!
