Spend Friday at Demo Day with us, @fabianstelzer
, and Diwank Singh. We’ll be demo’ing GPT3 powered prompt generators on Google Sheets, satirical pitch decks, and more. Join our Discord to be a part of it:
PROMPT ENGINEERING
-
Demo Day: GPT-3 Powered Tools and Innovations
By
–
-
Few-shot Prompt Setup Notes for Scaling Law Experiments
By
–
Some setup notes (cc @EthanJPerez
) – We used the exact 2-shot prompt for Quote Repetition, which is already U-shaped for Gopher/Chinchilla – We used fewer shots for Hindsight – We did few-shot instead of 0-shot for Negation QA – We also showed inverse scaling up to PaLM 62B -
U-shaped Scaling and the Limitations of Inverse Scaling Tasks
By
–
Implications: 1. U-shaped scaling means that inverse scaling may not hold when extrapolated to larger models. 2. The term “inverse scaling task” is underspecified. A task can be inverse scaling for one type of prompting and positive or U-shaped for another type of prompting.
-
CoT Prompting Defends Against Inverse Scaling in Math Tasks
By
–
Second, we show that CoT prompting can defend against inverse scaling. For instance, CoT prompting achieves 100% on 7 out of 8 subtasks for Redefine Math.
-
Using StableBoost to refine image generation through visual selection
By
–
e.g. I used stableboost for this earlier tweet 🙂 – the prompt by itself gives bad, too diverse, not amazing results, but once I generated ~1000 I could visually narrow in on the composition I liked. Not sure how I'd get that by tuning the prompt alone
-
Visual Iteration Over Text Prompts for AI Image Generation
By
–
Sometimes it's difficult to put the look&feel of what you're after into text. You end up re-rolling results over and over again, looking for the needle in a haystack. stableboost flips it around – you create a large haystack of variations, then narrow in on the needle visually.