Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
GRPO: Rust LLM Training
This talk demonstrates using Cargo feedback to create a training pipeline that improves large language models on low-resource languages like Rust through reinforcement learning.
I am putting together a training pipeline to improve LLMs on low resource languages like rust
Related projects
Real-Time AI Infrastructure for the Multi-Agent Era: Building AG-UI Protocol in Pure Rust
Los Angeles
Learn how the AG‑UI protocol enables real‑time AI agent‑to‑UI communication using Rust and WebAssembly, providing sub‑10 ms cold starts,…
CorpusKeeper - Talk To Data
Seattle
Demonstrating how to integrate LLMs, RAG, and function calls to create an agency‑style interface that designs, scripts, and…
CrustyCrab: An Experimental LLM-based C-to-Rust Translator
New York City
This talk explores using large language models to translate legacy C code into safe, idiomatic Rust, improving memory…
Event concierge
Los Angeles
The talk demonstrates how to parse emails with LLMs to extract event details, generate structured outputs, and preview…
Long term and short term memory
Los Angeles
A demo of a Gradio interface using ChromaDB to store and retrieve conversation embeddings, enabling long‑term memory with…
Better Insights into Team Activity
Los Angeles
The session demonstrates a Jupyter Notebook proof‑of‑concept that combines usage‑tracking dashboards, forecasting models, and a retrieval‑augmented LLM to…