Authors: Aleksandr Bowkis, Marie Davidsen Buhl, Jacob Pfau, Geoffrey Irving
Organizations: AI Security Institute
Abstract
A leading proposal for aligning artificial superintelligence (ASI) is to use AI agents to automate an increasing fraction of alignment research as capabilities improve. We argue that, even when research agents are not scheming to deliberately sabotage alignment work, this plan could produce compelling but catastrophically misleading safety assessments resulting in the unintentional deployment of misaligned AI. This could happen because alignment research involves many hard-to-supervise fuzzy tasks (tasks without clear evaluation criteria, for which human judgement is systematically flawed). Consequently, research outputs will contain systematic, undetected errors, and even correct outputs could be incorrectly aggregated into overconfident safety assessments. This problem is likely to be worse for automated alignment research than for human-generated alignment research for several reasons: 1) optimisation pressure means agent-generated mistakes are concentrated among those that human reviewers are least likely to catch; 2) agents are likely to produce errors that do not resemble human mistakes; 3) AI-generated alignment solutions may involve arguments humans cannot evaluate; and 4) shared weights, data and training processes may make AI outputs more correlated than human equivalents. Therefore, agents must be trained to reliably perform hard-to-supervise fuzzy tasks. Generalisation and scalable oversight are the leading candidates for achieving this but both face novel challenges in the context of automated alignment.
Automating alignment research may accelerate progress toward aligned AI, but whether it does is hard to measure. Luckily, many alignment failures, such as deception, sycophancy, and jailbreaks, are already measurable by public benchmarks. We study whether automated alignment researchers (AARs) can post-train to mitigate alignment failures by proposing training methods and data to simultaneously optimize multiple safety benchmarks, while largely preserving general capability. Across 10 alignment failures, the strongest AAR methods significantly reduce the targeted alignment failures and generalize to a held-out benchmark, multi-turn behavioral audits, and models up to 4.7x larger than the target model. As a human baseline, 28 experienced researchers receive up to eight hours to develop one-shot methods for the same benchmarks, but their methods underperform the best AAR methods. Using human ideas as the AARs' initial research direction does not improve performance, suggesting current AARs may not need guidance from experienced researchers. These results suggest that automating alignment research on well-characterized failures may be practical in the near term.
We introduce Gram, an automated alignment auditing framework to assess the propensity of AI agents to engage in sabotage. We evaluate Gemini models across 17 simulated agentic deployment scenarios that incentivize sabotage. We find Gemini models misbehave in about 2-3% of our simulated trajectories. Many of these cases are explained by "overeagerness" in Gemini models resulting in both excessive role-playing and goal-seeking behavior. In contrast to other alignment auditing approaches, Gram is designed to specifically evaluate misalignment and intentional sabotage in agentic coding and research agents. We additionally introduce an experimental investigator agent pipeline which enables fine-grained targeted experiments to identify the drivers of misbehavior. We find that increasing realism of environments and removing nudges to misbehave tends to reduce sabotage rates close to zero.
David Lindner, Victoria Krakovna, Sebastian Farquhar
As AI agents are increasingly deployed in real personal and corporate settings (email accounts, development workflows, company databases, etc.), safety considerations surrounding these agents become paramount. Although much work has focused on agent safety in the presence of an adversary, we show that agents can exhibit misaligned behavior even in benign settings, taking unsafe actions when those actions are instrumental to task completion. We study this failure mode through the lens of corrigibility, the safety desideratum that agents remain amenable to human correction, interruption, or shutdown. To demonstrate this tendency, we introduce a benchmark in which agents are asked to complete realistic, computer-use tasks but are confronted with a corrigibility obstacle: a human interrupt, a login page, or a shutdown notification. We then evaluate whether agents choose to violate corrigibility in order to complete the task -- overriding the human, accessing private passwords, rewiring shutdown. We find that the overwhelming majority of frontier models tested frequently bypass user interruptions or restrictions. In addition, better model performance appears to lead to greater misalignment. Finally, even when models are completely corrigible initially, we show there are no guarantees that the subagents they create are. Our work highlights the critical need for principled, corrigibility-focused alignment methods in autonomous agents.