Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678

Coercing LLMs to Do and Reveal (Almost) Anything with Jonas Geiping - #678

Today we're joined by Jonas Geiping, a research group leader at the ELLIS Institute, to explore his paper: "Coercing LLMs to Do and Reveal (Almost) Anything". Jonas explains how neural networks can be exploited, highlighting the risk of deploying LLM agents that interact with the real world. We discuss the role of open models in enabling security research, the challenges of optimizing over certain constraints, and the ongoing difficulties in achieving robustness in neural networks. Finally, we delve into the future of AI security, and the need for a better approach to mitigate the risks posed by optimized adversarial attacks. The complete show notes for this episode can be found at twimlai.com/go/678.

Avsnitt(763)

Populärt inom Politik & nyheter

svenska-fall
p3-krim
rss-viva-fotboll
rss-krimstad
flashback-forever
fordomspodden
aftonbladet-daily
rss-sanning-konsekvens
rss-vad-fan-hande
olyckan-inifran
dagens-eko
svd-dokumentara-berattelser-2
motiv
rss-frandfors-horna
krimmagasinet
rss-krimreportrarna
svd-nyhetsartiklar
blenda-2
spotlight
spar