All videos

AI Alignment is More Fragile Than You Think (And Shaggoth is Lurking)

September 30, 2025

One of the fundamental features of LLMs is their ability to provide responses aligned with human ethical principles and intentions. In his talk, Przemek will explore what LLMs truly "know" about morals, discuss how models are being trained for AI Alignment, and reveal how (surprisingly) easy it is to break. He'll show experimental results, in which a small set of harmful examples could derail alignment. A live demo and open discussion on what it all means for us will follow.

About the speaker

Przemek Maciolek

Przemek Maciolek

Staff Software Engineer
By day, working on Data Engineering at a major Home-sharing Platform. In past lives, worked for numerous startups, where he was a founding engineer, principal…
Read more

Other videos that you might like

fallback image
BUGinnings in IT
Culture shock – how to find yourself in IT when starting your first job
Adrianna Woltmann
fallback image
Reactive systems
Practical Reactive Streams with Monix
Jacek Kunicki
fallback image
Cloud
Automate Azure DevOps update with Azure Functions
Menaka Basker
fallback image
Frontend/JS
IA behind the scenes – when UX meets Dev to create a reliable Information Architecture
Monika Soja, Tomasz Piechaczek
All videos