Aaron Sandoval

The field of AI Control seeks to develop robust control protocols, deployment safeguards for untrusted AI which may be intentionally subversive. However, existing protocols that rely on weaker monitors to detect unsafe behavior often fail on complex tasks beyond the monitor's comprehension. We develop control protocols based on factored cognition, in which a trusted model decomposes a task, an untrusted model solves each resultant child task in isolation, and the results are reassembled into a full solution. These protocols may improve safety by several means, such as by simplifying the context for monitors, or by obscuring vulnerabilities in the environment. We implement our protocols in the APPS coding setting and red team them against backdoor attempts from an adversarial GPT-4.1 Nano. We find that: (i) Adding factored cognition to a trusted monitoring protocol can boost safety from 41% to 63%; (ii) Safety improves because monitor performance improves; (iii) Factored cognition makes it no harder for capable LLMs to write backdoors in APPS. While our protocols show low usefulness in APPS, they hold promise for more complex tasks.

As AI capabilities advance, we increasingly rely on powerful models to decompose complex tasks $\unicode{x2013}$ but what if the decomposer itself is malicious? Factored cognition protocols decompose complex tasks into simpler child tasks: one model creates the decomposition, while other models implement the child tasks in isolation. Prior work uses trusted (weaker but reliable) models for decomposition, which limits usefulness for tasks where decomposition itself is challenging. We introduce Factor($U$,$T$), in which an untrusted (stronger but potentially malicious) model decomposes while trusted models implement child tasks. Can monitors detect malicious activity when observing only natural language task instructions, rather than complete solutions? We baseline and red team Factor($U$,$T$) in control evaluations on BigCodeBench, a dataset of Python coding tasks. Monitors distinguishing malicious from honest decompositions perform poorly (AUROC 0.52) compared to monitors evaluating complete Python solutions (AUROC 0.96). Furthermore, Factor($D$,$U$), which uses a trusted decomposer and monitors concrete child solutions, achieves excellent discrimination (AUROC 0.96) and strong safety (1.2% ASR), demonstrating that implementation-context monitoring succeeds where decomposition-only monitoring fails.