Token of Power (ToP)
Leo Karoubi, Quentin Feuillade--Montixi · Team The fellowship of the token
Submitted to AI Control Hackathon 2025. Sprint projects are early-stage work by participants, not Apart Research publications.
Token of Power demonstrates a new approach to AI capability control where models learn their own gating mechanisms through training, rather than relying on manual restrictions. By using specialized "capability tokens" as access keys, we can maintain full model capabilities while enabling precise control over specific behaviors. Our proof-of-concept shows this approach working reliably even on a small 1B parameter model, suggesting a path toward more nuanced AI control systems.
Reviews
No public critique yet.
Cite this project
@misc{karoubi2025token,
title = {{Token of Power (ToP)}},
author = {Leo Karoubi and Quentin Feuillade--Montixi},
year = {2025},
month = mar,
note = {Submitted to AI Control Hackathon 2025, an Apart Research Sprint},
howpublished = {\url{https://apartresearch.com/sprints/projects/token-of-power-top-4ome}},
url = {https://apartresearch.com/sprints/projects/token-of-power-top-4ome}
}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 …
- 3rd place by peer reviewView project: Model Models: Simulating a Trusted Monitor
Model Models: Simulating a Trusted Monitor
Charlie's Angels
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 …