Model Models: Simulating a Trusted Monitor
Louis Thomson, Alex Holness-Tofts, Jasmijn Remmers, Xanthe Spence, Lennie Wells, Charlie Griffin · Team Charlie's Angels
Submitted to AI Control Hackathon 2025. Sprint projects are early-stage work by participants, not Apart Research publications.
We offer initial investigations into whether the untrusted model can 'simulate' the trusted monitor: is U able to successfully guess what suspicion score T will assign in the APPS setting? We also offer a clean, modular codebase which we hope can be used to streamline future research into this question.
Reviews
No public critique yet.
Cite this project
@misc{thomson2025model,
title = {{Model Models: Simulating a Trusted Monitor}},
author = {Louis Thomson and Alex Holness-Tofts and Jasmijn Remmers and Xanthe Spence and Lennie Wells and Charlie Griffin},
year = {2025},
month = mar,
note = {Submitted to AI Control Hackathon 2025, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/model-models-simulating-a-trusted-monitor-r682}},
url = {https://apartresearch.com/sprints/projects/model-models-simulating-a-trusted-monitor-r682}
}More from AI Control Hackathon 2025
- 1st place by peer reviewView project: Can models use their Chain-of-Thought to attack overseers?
Can models use their Chain-of-Thought to attack overseers?
This project explores vulnerabilities in AI evaluation mechanisms, specifically focusing on how AI agents might influence their overseeing AI judges through manipulative instructions embedded within their …
- 2nd place by peer reviewView project: Schelling coordination via agentic loops
Schelling coordination via agentic loops
Focal
Capability to collude undermines untrusted monitoring protocols. We propose a novel way to evaluate acausal coordination capabilities of LLMs via repeated sampling in causally separated agentic loops. We provide an …
- 4th place by peer reviewView project: Adding Document Summaries to Control Arena
Adding Document Summaries to Control Arena
One of the current focuses of AI Control research is finding new settings within which to examine the control problem. In this hackathon, we looked at defining a new AI control setting based around summarizing documents …