Prompt Stretching: Applying Linear Transformations and Recursive Decomposition to Prompts | Los Angeles .
Cities (231) ▾

Members-Only

Recent Talks & Demos are for members only

Exclusive feed

You must be an AI Tinkerers active member to view these talks and demos.

Sign in View FAQ
March 19, 2026 · Los Angeles

Prompt Stretching: Applying Linear Transformations and Recursive Decomposition to Prompts

Explore a Python library that transforms prompts using linear algebra and recursive decomposition, enabling LLMs to generate other LLMs and build deep research agents.

Python LLM OpenAI API Anthropic API JSON
Overview

I’ll walk through an open source Python library I’m working on where LLMs generate other LLMs as reusable JSON configs. The core demo is “prompt stretching” — a pipeline that takes a single user prompt and fans it out through a family tree of transformations (inverse, abstract up/down, reflection, rotation, shear, scaling, recursion, dimension shift). Then I’ll also demo subprompting — recursively decomposing a prompt into a tree of subprompts at configurable depth and branching factor (e.g. n=[4,3,2]), with concurrent execution, so anyone can build their own deep research agent. Finally, all the transformed/decomposed prompt variants and their responses can be pairwise evaluated.

Tech stack
  • Python
    Python: The high-level, general-purpose language built for readability, powering everything from web backends to advanced machine learning models.
    Python is the high-level, general-purpose language prioritizing clear, readable syntax (via significant indentation), ensuring rapid development for any team . Its ecosystem is massive: use it for robust web development with frameworks like Django and Flask, or leverage its power in data science with libraries such as Pandas and NumPy . The Python Package Index (PyPI) provides thousands of community-contributed modules, offering immediate solutions for tasks from network programming to GUI creation . The language is actively maintained by the Python Software Foundation (PSF), with the stable release currently at Python 3.14.0 (as of November 2025) .
  • LLM
    Large Language Models (LLMs) are deep learning models, built on the Transformer architecture, that process and generate human-quality text and code at scale.
    LLMs are a class of foundation models: massive, pre-trained neural networks (often with billions to trillions of parameters) that leverage the self-attention mechanism of the Transformer architecture (introduced in 2017) to predict the next token in a sequence. Trained on vast datasets (e.g., Common Crawl's 50 billion+ web pages), these models—like GPT-4, Gemini, and Claude—acquire predictive power over syntax and semantics. They function as general-purpose sequence models, enabling critical applications such as complex content generation, language translation, and automated code completion (e.g., GitHub Copilot). Their core value: generalizing across diverse tasks with minimal task-specific fine-tuning.
  • OpenAI API
    OpenAI API: Your direct gateway to cutting-edge AI models (GPT-4o, DALL-E 3, Whisper), enabling scalable, multimodal intelligence integration into any application.
    The OpenAI API provides authenticated, programmatic access to a powerful suite of generative AI models. Developers leverage REST endpoints and official libraries (Python, Node.js) to integrate capabilities like advanced text generation (GPT-4o), image creation (DALL-E 3), and speech-to-text transcription (Whisper). This platform is engineered for scale, supporting millions of daily requests for tasks from complex reasoning to real-time customer support agents, ensuring your application gets reliable, state-of-the-art intelligence.
  • Anthropic API
    Programmatic access to Anthropic's Claude models (Opus, Sonnet, Haiku) for complex reasoning, vision, and tool-use applications.
    The Anthropic API delivers programmatic access to the Claude model family (Opus, Sonnet, Haiku), enabling developers to integrate state-of-the-art AI into applications. Use the Messages API for conversational tasks, leveraging Claude 3.5 Sonnet for balanced performance or Claude 3 Opus for complex analysis. Key features include Tool Use (function calling), Vision capabilities for image analysis, and a large 200K token context window for extensive document processing. This API provides a powerful, reliable foundation for next-generation AI projects.
  • JSON
    JSON (JavaScript Object Notation): A lightweight, language-independent data format for structured data interchange, built on universally supported key-value pairs and ordered arrays.
    JSON is the standard for modern data exchange, leveraging human-readable text to transmit structured information. Its minimal syntax uses two core types: objects (unordered collections of name:value pairs, like {"user": "alpha"}) and arrays (ordered lists of values, like [1, 2, 3]). This structure, derived from JavaScript, ensures efficient parsing and generation across all major programming languages (e.g., Python, Java, Go). We deploy JSON extensively: it is the de facto payload for RESTful APIs and the preferred format for application configuration files (e.g., package.json). The current specification (RFC 8259) ensures consistent, high-scale interoperability.
Events Gallery FAQ Sponsor