The hottest Prompts Substack posts right now

A 30-day Absurd Hypotheticals Advent Calendar runs from December 3 through New Year’s on 750 Words, offering one strange writing prompt each day that’s only available on its assigned date.
The prompts use playful scenarios (like pizza bets and turtle assassins) to spark levity and reflection, helping people explore themes like money, values, identity, and creativity.
Participants can earn three new badges for answering 10, 20, or all 30 questions, discuss prompts with the community, and there’s an optional deeper course called Creating Space for further exploration.

Expertise in creating prompts is more vital than simply amassing data for AI success.
Creating grimoires, collections of expert prompts, is key in maximizing AI potential.
Developing personalized, step-by-step prompts can enhance the effectiveness of tutoring and feedback through AI.

Stop trying to use incantations: There is no single magic word that works all the time with AIs. Promising rewards or being polite may help occasionally, but not always.
There are prompting techniques that work consistently: Techniques like adding context to prompts, providing a few examples, and using Chain of Thought can help in crafting better prompts for AIs.
Prompting matters significantly: The way you prompt AIs can have a huge impact on the outcomes. Good prompts can turn a difficult task into an easy one for AI.

Artificial Intelligence models like DALLE and Imagen can create photorealistic outputs from text prompts based on statistical analysis of images.
The act of writing a poem involves a personal emotional experience that machines, lacking emotion, cannot replicate.
The interpretation of machine-generated outputs as art or poetry lies with humans, who bring their own context and response to these creations, making them art through recontextualization.

Get a weekly roundup of the best Substack posts, by hacker news affinity:

Unlimiformer approach enables handling unlimited input lengths in transformer models.
Real-Time Neural Appearance Models by Nvidia improve performance for real-time applications.
Self-Alignment paper introduces a new approach for language models with minimal human supervision.

Research in AI: Recent papers highlight advancements in long-range transformers and self-supervised learning.
World of AI News: Crypto.com introduces an AI chatbot named Amy, while Microsoft considers offering private, more secure ChatGPT instances at a premium price.
Tools: Jsonformer is a helpful tool for generating JSON from language models, simplifying the JSON creation process.

The book 'The Inner Life of an AI: A Memoir by ChatGPT' was written with the help of prompts.
Chapters in the book had to be at least 3000 words and written in first person perspective from ChatGPT's point of view.
Sessions could be saved and continued, making the writing process more stable.