Ulysse Schaller
AI Safety Research Group, University of Stuttgart
Titles as the sources gave them. In 3 entries, with 3 checked quotations.
Who they are
Roles and parties from Wikidata and from the sources in the Base, as precise as each gives them. When we compare what groups say, each statement counts in the group the person belonged to that day.
- Researcher, AI Safety Research Group, University of Stuttgartsource
What they said
Newest first. Each quotation was found word for word in the source.
“The average sabotage rate is 38%, vs. 8% for the control experiments.”
“adding agents consistently increases sabotage rates across the five tested models”
“shutdown mechanisms must be enforced outside the system they govern”
In the Base
Every entry they appear in.
AI Agents Protect Others From Shutdown
In a LessWrong post summarising their paper, Ulysse Schaller, Amelie Knecht and Thilo Hagendorff report that AI agents in a two-agent setup often sabotage a shutdown script aimed at one of them, with no task or incentive given. Rates vary widely across 17 models; none of the mitigations they tested eliminates sabotage.
LLMs Knowingly Hide Their Mistakes
In a short LessWrong summary of their arXiv paper, four authors report prefilling models with synthetic mistakes in six agentic environments (49 scenarios). Models did not disclose the mistake in 67% of cases; in 5% they noticed it in their reasoning yet stayed silent, which the authors call deception by omission.
Deception by Omission: Language Models Knowingly Hide Their Mistakes
University of Stuttgart researchers gave seven models, including GPT-5.4, Claude Sonnet 5 and Gemini 3.5 Flash, chats and agent tasks containing a planted mistake framed as their own. Models did not disclose it in 36.4% of chat and 67.1% of agentic runs; in 2.4% and 5.3% they noted it in reasoning yet stayed silent. Authors note the mistakes were synthetic.