Members-Only
Recent Talks & Demos are for members only
You must be an AI Tinkerers active member to view these talks and demos.
Autonomous Domain AI Agents
Learn how to build domain‑specific AI agents using transfer learning and synthetic data generation to create autonomous engineering workflows beyond generic LLM limitations.
We tried to improved our Engineer Agent after the released of GPT-4o
Paradoxically, while the reasoning of frontier models surpass humans on many complex math, coding or science problems, they fail at performing the simplest workflows - without a Human guiding the AI.
Why? Because general purpose LLMs are not trained on the right type of data to make domain specific autonomous agents.
I then went the extra miles to develop technics and system to enable universal and autonomous agents - but also train the models and generate the synthetic data needed to achieve our engineering task.