Making PDFs editable, using typst, LLMs and crazy fast inference | Seattle .

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.

January 31, 2026 · Seattle

typst: Editable PDFs via LLMs

Demoing a tool converting PDFs to editable Typst code, enabling fast, structure-preserving, context-aware edits via a custom cursor interface.

Overview
Tech stack
  • Typst
    Typst: The open-source, markup-based typesetting system; it delivers LaTeX power with superior speed and integrated scripting.
    Typst is a modern, open-source typesetting system built to replace complex tools like LaTeX: it offers a powerful, intuitive markup language with a tightly integrated scripting system. Its Rust-based compiler delivers blazing-fast, incremental compilation (milliseconds) for instant previews, generating professional PDFs, PNGs, and SVGs. The platform supports first-class mathematics, comprehensive bibliography management (e.g., Zotero sync), and a collaborative web application, making it the efficient choice for technical and scientific document creation.
  • Gemini 3
    Gemini 3 Pro: Google's most intelligent, state-of-the-art multimodal AI model, engineered for advanced reasoning and complex agentic coding workflows.
    This is the third-generation model, the new intelligence foundation for Google's ecosystem. Gemini 3 Pro delivers state-of-the-art reasoning and world-leading multimodal understanding: it seamlessly processes text, images, video, audio, and code. It is our most powerful agentic and vibe-coding model yet, designed to handle long-horizon, multi-step tasks; it features an industry-leading 1 million token context window. The model's performance is validated by its breakthrough score of 1501 Elo on the LMArena Leaderboard, confirming its superior capability for developers building on platforms like Vertex AI and the new Google Antigravity.
  • Qwen 235B
    Qwen3-235B-A22B is the flagship large language model from the Qwen3 series, running on a highly efficient Mixture-of-Experts (MoE) architecture
    Qwen3-235B-A22B is the flagship large language model from the Qwen3 series, running on a highly efficient Mixture-of-Experts (MoE) architecture. The system utilizes 235 billion total parameters, activating only 22 billion per inference for optimized performance. Its core innovation is the seamless, single-model switch between a resource-intensive *thinking mode* (for complex logic, math, and code) and an efficient *non-thinking mode* (for general dialogue). This model delivers competitive benchmark results against top-tier models like Gemini-2.5 Pro, showcasing superior reasoning, agent capabilities, and robust multilingual support across over 100 languages.
  • Rust
    Rust is a high-performance systems programming language that guarantees memory and thread safety via its compile-time ownership model.
    Rust is a statically-typed systems language engineered for performance and reliability, directly challenging C/C++ in speed. Its core innovation is the ownership model and 'borrow checker,' which enforces strict memory and thread safety at compile-time, eliminating data races and null pointer dereferences without a conventional garbage collector. Rust achieves near-native speed through 'zero-cost abstractions,' allowing high-level features to compile into highly optimized code. Major industry players, including Microsoft and Cloudflare, leverage Rust for critical infrastructure, and it is now officially supported for development in the Linux kernel.
  • TypeScript
    TypeScript is an open-source superset of JavaScript: it adds static typing and compiles to clean, standards-based JavaScript.
    TypeScript is a high-level, open-source language developed by Microsoft: it acts as a superset of JavaScript, adding a powerful static type system. This system enables compile-time type checking, catching errors before runtime (a critical benefit for large-scale applications). The TypeScript Compiler (TSC) reliably transpiles all code into clean, standards-based JavaScript (ES3 or newer), ensuring compatibility across any browser or host environment (Node.js, React.js, etc.).

Related projects