2025-12-09 –, Planck-Bohr
Everyone talks about “trustworthy AI,” yet few approaches go beyond good intentions. This talk takes a practical look at why AI systems often fail our trust—and how probabilistic methods can fix that.
We’ll explore how to connect RxInfer, a probabilistic inference engine, with LLM agents through the Model Context Protocol (MCP). MCP provides a simple way for language models to interact with probabilistic reasoning tools, letting them move beyond confident guesses to quantified beliefs.
By embracing uncertainty rather than ignoring it, we can design AI systems that reason more transparently, admit their limits, and make decisions we can actually trust. Expect a blend of conceptual insight, Python demos, and a few honest laughs about the current “AI trust” hype.
Tired of hearing about “trustworthy AI”? So are we. This talk shows how to make it real—by marrying LLM agents with RxInfer’s probabilistic inference engine via the Model Context Protocol (MCP). Discover how embracing uncertainty, not denying it, leads to genuinely trustworthy AI systems.
Albert Podusenko is CEO of Lazy Dynamics, building RxInfer — a Bayesian inference engine for real-time, uncertainty-aware AI. He holds a PhD from TU Eindhoven in probabilistic machine learning.