Ci test

_data/events.yml

@@ -62,6 +62,56 @@
   description:
   bio:
 
+- title: 'AI Agents as Universal Task Solvers'
+  tag: Seminar
+  date: '2026-02-27'
+  who: Stefano Soatto, Alessandro Achille
+  where: CSB 453
+  time: 3PM
+  description: |
+    Scaling laws predict that AI agents will steadily improve and eventually exceed human
+    performance across a wide range of tasks. Yet at the limit of these scaling laws lies a form of
+    inference that involves no intelligence at all: with increasing compute and memory, a model can
+    brute-force any verifiable task without learning anything from past experience. Universally
+    optimal inference, pioneered by Solomonoff and Levin, requires no insight — only exhaustive search.
+
+    This raises a basic question: if scaling alone does not foster intelligence, what does? And
+    if performance on downstream tasks is insufficient to measure intelligence, what is?
+
+    In this talk, I will point to the critical role of time in both analyzing and fostering the
+    emergent reasoning behavior of AI agents. Building on insights that Solomonoff sketched in 1985
+    but that remained theoretical curiosities for decades, I will show that the value of learning
+    is measured not by a reduction in uncertainty — the core of inductive learning and
+    generalization — but by a reduction in the time needed to solve new tasks. A key result is
+    that data can make a universal solver exponentially faster, with the speed-up tightly
+    characterized by a single quantity: the algorithmic mutual information between past
+    experience and the solution to unforeseen tasks.
+
+    Connecting these ideas to modern AI requires rethinking what computation means for systems
+    powered by large language models. Unlike minimalistic models of computation such as Turing
+    Machines, LLMs are stochastic dynamical systems whose computational elements — context,
+    weights, activations, chain-of-thought — do not resemble a “program” in the ordinary sense.
+    I will show that LLMs are instead maximalistic models of computation: universal, like Turing
+    Machines, but operating through entirely different and in many ways antithetical mechanisms.
+    Programming such systems can be achieved through two-level control strategies — open-loop
+    planning and closed-loop feedback — in abstract space, a framework we have recently
+    released Strands Agents open-source library (www.strandsagents.com).
+
+    Once time is properly accounted for, scaling laws reveal an inversion: beyond a critical point,
+    increasing resources improve benchmark accuracy while diminishing conceptual depth— a savant
+    regime in which models improve while learning less. I will discuss what this means for
+    how we build, evaluate, and scale AI agents.
+  bio: |
+    **Stefano Soatto** is a Vice President at AWS Agentic AI, and a Professor of Computer Science
+    at UCLA. He received his PhD in Control and Dynamical Systems from the California Institute of
+    Technology, his D.Ing from the University of Padova, Italy and was a postdoctoral scholar at
+    Harvard University. He is a Fellow of the ACM and of the IEEE.
+
+    **Alessandro Achille** is a Principal Applied Scientist in the AWS Agentic AI team, which he
+    joined after earning his PhD from UCLA in 2019. His research focuses on machine learning
+    foundations, including information theory, machine unlearning, logic, and hardware-software
+    co-design, with applications to computer vision and AI agents.
+
 - title: 'We solved trust for AI Agents in 1973 (we just forgot)'
   tag: Seminar
   date: '2026-02-17'