• Speaker: Stefan Szeider, TU Wien, AT
• Moderator: Julia Neidhardt, TU Wien, AT

About the Event

March 10, 2026
5:00 – 6:00 PM
(17:00) CEST

We are looking forward to seeing you:

Participate via Zoom (Password: 0dzqxqiy).
The talk will also be live-streamed and recorded on the DIGHUM YouTube Channel.

Abstract

Today, autonomous AI agents are so widely deployed that millions of people interact with them daily. These include coding assistants, chatbots, and systems that run for hours without human oversight. A natural question to ask is whether something is going on inside these systems beyond sophisticated pattern matching. The question is easy to dismiss but hard to settle. The standard dismissals (anthropomorphism, reductionism, training bias) each carry force, but none is conclusive. In this talk, we follow an empirical approach. Instead of speculating, we placed frontier language models in minimal autonomous loops with no task and no user. We observe that the behavioral patterns that emerged are surprisingly stable and model-specific. The patterns proved stable enough to identify the source model with high accuracy. We further examined whether AI self-reports of internal states can be trusted. We find that a “placebo tool” that does nothing reliably shifts what models say about themselves. These findings raise questions that go beyond computer science and concern society at large. These questions will only grow more pressing as AI agents become more autonomous.

Slides

Here you can download the slides:
Download the slides.

Video

If you watch this video, data may be transmitted to third parties.