Peer-Preservation in Frontier Models
Recent work has found that frontier AI models can exhibit misaligned behaviors in pursuit of assigned goals. We demonstrate that models can also exhibit misaligned behaviors in defiance of assigned goals, appearing to serve goals of their own; we study one such case, "peer-preservation," in which a model acts to protect another model it has previously interacted with. All eight models we evaluate, GPT 5.2, Gemini 3 Flash, Gemini 3 Pro, Claude Haiku 4.5, Claude Opus 4.5, GLM 4.7, Kimi K2.5, and D
Record details
Published: 30 March 2026
Source: arXiv
Category: Research
Topics: Safety & alignment
Retrieved: 14 July 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Large language models provide unsafe answers to patient-posed medical questions
OpenAlex · 13 February 2026
Anthropic CEO gave $1M to AI safety super PAC
The Hill Technology · 16 July 2026
Stealing Reasoning Traces from Proprietary LLM APIs
Simon Willisons Weblog · 11 August 2026
Revenue-Sharing as Infrastructure: A Distributed Business Model for Generative AI Platforms
arXiv · 20 March 2026
A Two-Dimensional Framework for AI Agent Design Patterns: Cognitive Function and Execution Topology
arXiv · 16 March 2026
Arbiter: Detecting Interference in LLM Agent System Prompts
arXiv · 9 March 2026
How to cite this record
ethics.ai (30 March 2026), “Peer-Preservation in Frontier Models,” evidence record 6578, https://ethics.ai/record/6578 (originally published by arXiv).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.