[Epistemic status: slightly rambly, mostly personal intuition and opinion that will probably be experimentally proven wrong within a year considering how fast stuff moves in this field] Thanks to Gwe| Leo Gao
Simulacra and simulation in self-supervised models| generative.ink
"Actualities seem to float in a wider sea of possibilities from out of which they were chosen; and somewhere, indeterminism says, such possibilities exist, and form part of the truth."| generative.ink
Measuring optimization from curation| generative.ink
Combining multipart prompts, logit biases, and counterfactual parsing to make GPT-3 emulate fake Google search results given a query / Wikipedia pages given a title| generative.ink
Context-aware parsing using counterfactual probabilities predicted by GPT-3| generative.ink
Improving GPT-3's performance on SAT analogy questions using task-agnostic prompt pipelines| generative.ink
How to get GPT-3 to sort a list: make it think it's a python interpreter running list.sort()| generative.ink
What GPT-3 Prompt Engineering is, why it matters, and some tips and tricks to help you do it well.| andrew makes things