David Schmotz

mentions 2 type Person feed RSS

// recent coverage 2 mentions

15:01

2026-09-19

pub.towardsai.net

artificial-intelligence

Your AI Agent’s Reasoning Isn’t as Private as You Think

A team from the ELLIS Institute Tübingen and the Max Planck Institute for Intelligent Systems published a paper in August titled "Stealing Reasoning Traces from Proprietary LLM APIs" showing that encr…

17:47

2026-08-11

runtimewire.com

ai-safety

OpenAI, Anthropic and Google blocked a cross-model reasoning attack

Researchers Alexander Panfilov, David Schmotz, and Ilia Shumailov found a way to recover encrypted reasoning from models by OpenAI, Anthropic, and Google, as detailed in a paper posted on August 10th.…

// co-occurs with top 8 entities

Max Planck Institute for Intelligent Systems 2 Alexander Panfilov 2 Ilia Shumailov 2 OpenAI 2 ELLIS Institute Tübingen 1 Luca Beurer-Kellner 1 Matthew Green 1 Anthropic 1

// topics top 5 topics

artificial intelligence 2 ai safety 2 ai research 2 large language models 1 ai agents 1