August 10th, 2024

Apple Intelligence System Prompts

The GitHub repository features Apple Intelligence's text processing capabilities in macOS Sequoia 15.1 Developer Beta, including summarization, story generation, email responses, and structured conversational support with detailed JSON prompts.

Read original articleLink Icon
Apple Intelligence System Prompts

The GitHub repository contains system prompts from Apple Intelligence related to the macOS Sequoia 15.1 Developer Beta, highlighting various text processing functionalities. Key features include the ability to make text more concise, generate human-like stories from user photos, and transform text into bullet points. It enhances readability and friendliness, summarizes text snippets, and creates concise email responses. The system supports structured responses for guided conversations, renames text in different styles, and processes search queries for improved understanding. Additionally, it can generate conversational turns in chat interactions and create vivid scenes from user photos. The repository also provides JSON files detailing specific prompts and their purposes.

- The repository showcases Apple Intelligence's text processing capabilities.

- Key functionalities include summarization, story generation, and email response generation.

- It supports structured responses and enhances text readability.

- JSON files in the repository detail specific prompts and their uses.

- The system can adapt text to different tones and styles based on user instructions.

Link Icon 7 comments
By @simonw - 6 months
Suggestion for this repo: prompts embedded in JSON files are quite hard to read, especially in mobile browsers.

You could add some code (perhaps in a GitHub Action) that extracts the prompts out into accompanying Markdown files to fix this.

You’ve already done most of the work to create this file: https://github.com/Explosion-Scratch/apple-intelligence-prom...

By @thomasfedb - 6 months
Seeing “Do not hallucinate.” included tells us a lot about AI in 2024.
By @DataDaemon - 6 months
I wonder why they write word "please", "please", "please". "Please limit the reply" "Please keep your summary" I think they don't know precisely how LLM works.
By @layer8 - 6 months
Doesn’t this repository constitute a copyright violation?