Tootfinder

Transition of AI Models in dependence of noise
Thomas Seidler, Markus Abel
https://arxiv.org/abs/2506.16715 https://arxiv.org/pdf/250…

Transition of AI Models in dependence of noise
We investigate the dependence of the score on noise in the data, and on the network size. As a result, we obtain the so-called "cognition transition" from good performance to zero with increasing noise. The understanding of this transition is of fundamental scientific and practical interest. We use concepts from statistical mechanics to understand how a changing finite size of models affects the cognition ability under the presence or corrupted data. On one hand, we study if there is a universa…

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
Brandon Jaipersaud, David Krueger, Ekdeep Singh Lubana
https://arxiv.org/abs/2508.05625

How Do LLMs Persuade? Linear Probes Can Uncover Persuasion Dynamics in Multi-Turn Conversations
Large Language Models (LLMs) have started to demonstrate the ability to persuade humans, yet our understanding of how this dynamic transpires is limited. Recent work has used linear probes, lightweight tools for analyzing model representations, to study various LLM skills such as the ability to model user sentiment and political perspective. Motivated by this, we apply probes to study persuasion dynamics in natural, multi-turn conversations. We leverage insights from cognitive science to train …

Chris Dillow on "Not Debating Immigration"
"Debates don't work, at least not as they should. They don't favour the truth, but plausible liars and for those who can best appeal to prejudice and cognitive bias."
To defeat the far right, people's living standards must improve Keir, Rachel & Liz.