Detecting scheming behaviour in multi-agent settings
-
Updated
Aug 23, 2025 - Python
#
deceptive-alignment
Here are 2 public repositories matching this topic...
Systematic probing toolkit for alignment-relevant LLM behaviors: sycophancy, sandbagging, power-seeking, deceptive alignment, and corrigibility failures
benchmark machine-learning evaluation alignment ai-safety ai-alignment llm rlhf sycophancy deceptive-alignment
-
Updated
Mar 3, 2026 - Python
Improve this page
Add a description, image, and links to the deceptive-alignment topic page so that developers can more easily learn about it.
Add this topic to your repo
To associate your repository with the deceptive-alignment topic, visit your repo's landing page and select "manage topics."