Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
React Compiler for LLMs
This talk explores building a React compiler optimized for LLM interaction, focusing on technical optimizations to improve performance through vertical integration.
I would give a talk on building a React compiler that’s optimized for interacting with LLMs. I want to highlight the opportunity that exists from creating optimizations in the toolkit that LLMs can use. I want to dive into what technical optimizations you can apply across a vertical level to achieve better performance.
Prototyper uses AI to generate React UI from text/image prompts.
Related projects
LLM Evaluations in Practice
Amsterdam
Learn about a practical setup for LLM evaluation in production, sharing hard-earned lessons for guiding prompt and code…
How to evaluate LLMs?
Amsterdam
This talk demonstrates practical methods to evaluate LLM outputs using judges, cosine similarity, and JSON schema validators to…
LLM.f90 - Minimal Large Language Model Inference Framework
Toronto
A low‑dependency Fortran framework for LLM inference, showing zero‑dependency implementation, matrix operations, and support for Llama, Phi, and…
Classifying Data with LLMs
Amsterdam
Learn how to use LLMs to generate categories and assign items, providing a practical alternative to traditional classifiers…
Managing UI for Generative AI in JavaScript
Amsterdam
Learn to manage generative AI streams in JavaScript by modeling retrieval and generation as state machines, and see…
Building AI react apps
Seattle
This talk demonstrates building a simple AI app using the Tambo dev tool, enabling AI to control and…