Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Handit: Automatic LLM Improvement
Learn how Handit lets an LLM monitor its output, detect weaknesses, and automatically update its parameters using real‑time feedback loops.
In this demo, we’ll showcase Handit, a tool to make any AI agent or LLM improve itself automatically. You’ll see how Handit enables models to monitor their performance, identify weaknesses, and adapt autonomously using real-time feedback. We’ll walk through the process of setting up a self-improving LLM, demonstrating how the platform analyzes outputs, detects areas for optimization, and evolves the model to handle new challenges. This isn’t just about monitoring—it’s about building smarter, dynamic AI systems that grow and improve on their own.
Handit.ai auto-optimizes AI agents through prompt generation, A/B testing, and deployment.
Related projects
Evolving Contexts: Applying Agentic Context Engineering for Self-Improving LLM Agents
Bogotá
A walkthrough of Agentic Context Engineering, showing how Generator, Reflector, and Curator iteratively refine context to counter brevity…
AnythingLLM: la plataforma integral para ejecutar modelos LLM locales y agentes de IA
Manizales
Demo of AnythingLLM: installing a local AI app, loading GGUF models, using RAG with PDFs/Word/CSV, and connecting OpenAI,…
Analisis de comentarios
Bogotá
This talk explores using Langchain and LLMs to analyze company comments cost-effectively, providing adaptable insights based on real…
Thinking LLMs
Los Angeles
This talk explains how to generate synthetic data for training custom o1 style language models using methods from…
Legal AI
Manizales
This talk covers developing a legal AI assistant using generative AI and retrieval-augmented generation to streamline legal research,…
Doing Precise and *Reliable* Automated Reasoning like It is 1972
Medellín
This talk compares modern LLMs' struggles with high-level logic puzzles to the effectiveness of symbolic AI methods like…