All videos
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.
Other videos that you might like
Pragmatic App Migration to the Cloud: Quarkus, Kotlin, Hazelcast and GraalVM in action
Nicolas Frankel
A software engineer in the land of data scientists
Rory Graves
Enterprise Final Frontier – is it possible to change the corporate ways in product development?
Monika Soja
Collaborative Filtering Microservices on Spark
Rui Vieira, Sophie Watson