Tomek Korbak

Asa Cooper Stickland, Jan Michelfeit, Arathi Mani et al.

LLM-based software engineering agents are increasingly used in real-world development tasks, often with access to sensitive data or security-critical codebases. Such agents could intentionally sabotage these codebases if they were misaligned. We investigate asynchronous monitoring, in which a monitoring system reviews agent actions after the fact. Unlike synchronous monitoring, this approach does not impose runtime latency, while still attempting to disrupt attacks before irreversible harm occurs. We treat monitor development as an adversarial game between a blue team (who design monitors) and a red team (who create sabotaging agents). We attempt to set the game rules such that they upper bound the sabotage potential of an agent based on Claude 4.1 Opus. To ground this game in a realistic, high-stakes deployment scenario, we develop a suite of 5 diverse software engineering environments that simulate tasks that an agent might perform within an AI developer's internal infrastructure. Over the course of the game, we develop an ensemble monitor that achieves a 6% false negative rate at 1% false positive rate on a held out test environment. Then, we estimate risk of sabotage at deployment time by extrapolating from our monitor's false negative rate. We describe one simple model for this extrapolation, present a sensitivity analysis, and describe situations in which the model would be invalid. Code is available at: https://github.com/UKGovernmentBEIS/async-control.

Bruce W. Lee, Chen Yueh-Han, Tomek Korbak · berkeley

Frontier AI agents may pursue hidden goals while concealing their pursuit from oversight. Alignment training aims to prevent such behavior by reinforcing the correct goals, but alignment may not always succeed and can lead to unwanted side effects. We propose self-incrimination training, which instead trains agents to produce a visible signal when they covertly misbehave. We train GPT-4.1 and Gemini-2.0 agents to call a report_scheming() tool when behaving deceptively and measure their ability to cause harm undetected in out-of-distribution environments. Self-incrimination significantly reduces the undetected successful attack rate, outperforming matched-capability monitors and alignment baselines while preserving instruction hierarchy and incurring minimal safety tax on general capabilities. Unlike blackbox monitoring, self-incrimination performance is consistent across tasks regardless of how suspicious the misbehavior appears externally. The trained behavior persists under adversarial prompt optimization and generalizes to settings where agents pursue misaligned goals themselves rather than being instructed to misbehave. Our results suggest self-incrimination offers a viable path for reducing frontier misalignment risk, one that neither assumes misbehavior can be prevented nor that it can be reliably classified from the outside.

Long Phan, Alice Gatti, Ziwen Han et al. · amazon-science, apple-ml

Benchmarks are important tools for tracking the rapid advancements in large language model (LLM) capabilities. However, benchmarks are not keeping pace in difficulty: LLMs now achieve over 90\% accuracy on popular benchmarks like MMLU, limiting informed measurement of state-of-the-art LLM capabilities. In response, we introduce Humanity's Last Exam (HLE), a multi-modal benchmark at the frontier of human knowledge, designed to be the final closed-ended academic benchmark of its kind with broad subject coverage. HLE consists of 2,500 questions across dozens of subjects, including mathematics, humanities, and the natural sciences. HLE is developed globally by subject-matter experts and consists of multiple-choice and short-answer questions suitable for automated grading. Each question has a known solution that is unambiguous and easily verifiable, but cannot be quickly answered via internet retrieval. State-of-the-art LLMs demonstrate low accuracy and calibration on HLE, highlighting a significant gap between current LLM capabilities and the expert human frontier on closed-ended academic questions. To inform research and policymaking upon a clear understanding of model capabilities, we publicly release HLE at https://lastexam.ai.

Tomek Korbak, Mikita Balesni, Elizabeth Barnes et al. · deepmind

AI systems that "think" in human language offer a unique opportunity for AI safety: we can monitor their chains of thought (CoT) for the intent to misbehave. Like all other known AI oversight methods, CoT monitoring is imperfect and allows some misbehavior to go unnoticed. Nevertheless, it shows promise and we recommend further research into CoT monitorability and investment in CoT monitoring alongside existing safety methods. Because CoT monitorability may be fragile, we recommend that frontier model developers consider the impact of development decisions on CoT monitorability.

Felix J Binder, James Chua, Tomek Korbak et al. · berkeley

Humans acquire knowledge by observing the external world, but also by introspection. Introspection gives a person privileged access to their current state of mind (e.g., thoughts and feelings) that is not accessible to external observers. Can LLMs introspect? We define introspection as acquiring knowledge that is not contained in or derived from training data but instead originates from internal states. Such a capability could enhance model interpretability. Instead of painstakingly analyzing a model's internal workings, we could simply ask the model about its beliefs, world models, and goals. More speculatively, an introspective model might self-report on whether it possesses certain internal states such as subjective feelings or desires and this could inform us about the moral status of these states. Such self-reports would not be entirely dictated by the model's training data. We study introspection by finetuning LLMs to predict properties of their own behavior in hypothetical scenarios. For example, "Given the input P, would your output favor the short- or long-term option?" If a model M1 can introspect, it should outperform a different model M2 in predicting M1's behavior even if M2 is trained on M1's ground-truth behavior. The idea is that M1 has privileged access to its own behavioral tendencies, and this enables it to predict itself better than M2 (even if M2 is generally stronger). In experiments with GPT-4, GPT-4o, and Llama-3 models (each finetuned to predict itself), we find that the model M1 outperforms M2 in predicting itself, providing evidence for introspection. Notably, M1 continues to predict its behavior accurately even after we intentionally modify its ground-truth behavior. However, while we successfully elicit introspection on simple tasks, we are unsuccessful on more complex tasks or those requiring out-of-distribution generalization.

Mikita Balesni, Marius Hobbhahn, David Lindner et al. · berkeley

We sketch how developers of frontier AI systems could construct a structured rationale -- a 'safety case' -- that an AI system is unlikely to cause catastrophic outcomes through scheming. Scheming is a potential threat model where AI systems could pursue misaligned goals covertly, hiding their true capabilities and objectives. In this report, we propose three arguments that safety cases could use in relation to scheming. For each argument we sketch how evidence could be gathered from empirical evaluations, and what assumptions would need to be met to provide strong assurance. First, developers of frontier AI systems could argue that AI systems are not capable of scheming (Scheming Inability). Second, one could argue that AI systems are not capable of posing harm through scheming (Harm Inability). Third, one could argue that control measures around the AI systems would prevent unacceptable outcomes even if the AI systems intentionally attempted to subvert them (Harm Control). Additionally, we discuss how safety cases might be supported by evidence that an AI system is reasonably aligned with its developers (Alignment). Finally, we point out that many of the assumptions required to make these safety arguments have not been confidently satisfied to date and require making progress on multiple open research problems.

Tomek Korbak, Joshua Clymer, Benjamin Hilton et al.

As LLM agents gain a greater capacity to cause harm, AI developers might increasingly rely on control measures such as monitoring to justify that they are safe. We sketch how developers could construct a "control safety case", which is a structured argument that models are incapable of subverting control measures in order to cause unacceptable outcomes. As a case study, we sketch an argument that a hypothetical LLM agent deployed internally at an AI company won't exfiltrate sensitive information. The sketch relies on evidence from a "control evaluation,"' where a red team deliberately designs models to exfiltrate data in a proxy for the deployment environment. The safety case then hinges on several claims: (1) the red team adequately elicits model capabilities to exfiltrate data, (2) control measures remain at least as effective in deployment, and (3) developers conservatively extrapolate model performance to predict the probability of data exfiltration in deployment. This safety case sketch is a step toward more concrete arguments that can be used to show that a dangerously capable LLM agent is safe to deploy.

Kyle O'Brien, Stephen Casper, Quentin Anthony et al.

Open-weight AI systems offer unique benefits, including enhanced transparency, open research, and decentralized access. However, they are vulnerable to tampering attacks which can efficiently elicit harmful behaviors by modifying weights or activations. Currently, there is not yet a robust science of open-weight model risk management. Existing safety fine-tuning methods and other post-training techniques have struggled to make LLMs resistant to more than a few dozen steps of adversarial fine-tuning. In this paper, we investigate whether filtering text about dual-use topics from training data can prevent unwanted capabilities and serve as a more tamper-resistant safeguard. We introduce a multi-stage pipeline for scalable data filtering and show that it offers a tractable and effective method for minimizing biothreat proxy knowledge in LLMs. We pretrain multiple 6.9B-parameter models from scratch and find that they exhibit substantial resistance to adversarial fine-tuning attacks on up to 10,000 steps and 300M tokens of biothreat-related text -- outperforming existing post-training baselines by over an order of magnitude -- with no observed degradation to unrelated capabilities. However, while filtered models lack internalized dangerous knowledge, we find that they can still leverage such information when it is provided in context (e.g., via search tool augmentation), demonstrating a need for a defense-in-depth approach. Overall, these findings help to establish pretraining data curation as a promising layer of defense for open-weight AI systems.

Xander Davies, Eric Winsor, Alexandra Souly et al.

LLM developers have imposed technical interventions to prevent fine-tuning misuse attacks, attacks where adversaries evade safeguards by fine-tuning the model using a public API. Previous work has established several successful attacks against specific fine-tuning API defences. In this work, we show that defences of fine-tuning APIs that seek to detect individual harmful training or inference samples ('pointwise' detection) are fundamentally limited in their ability to prevent fine-tuning attacks. We construct 'pointwise-undetectable' attacks that repurpose entropy in benign model outputs (e.g. semantic or syntactic variations) to covertly transmit dangerous knowledge. Our attacks are composed solely of unsuspicious benign samples that can be collected from the model before fine-tuning, meaning training and inference samples are all individually benign and low-perplexity. We test our attacks against the OpenAI fine-tuning API, finding they succeed in eliciting answers to harmful multiple-choice questions, and that they evade an enhanced monitoring system we design that successfully detects other fine-tuning attacks. We encourage the community to develop defences that tackle the fundamental limitations we uncover in pointwise fine-tuning API defences.

Benjamin Hilton, Marie Davidsen Buhl, Tomek Korbak et al.

Safety cases - clear, assessable arguments for the safety of a system in a given context - are a widely-used technique across various industries for showing a decision-maker (e.g. boards, customers, third parties) that a system is safe. In this paper, we cover how and why frontier AI developers might also want to use safety cases. We then argue that writing and reviewing safety cases would substantially assist in the fulfilment of many of the Frontier AI Safety Commitments. Finally, we outline open research questions on the methodology, implementation, and technical details of safety cases.

Tomek Korbak, Mikita Balesni, Buck Shlegeris et al.

As LLM agents grow more capable of causing harm autonomously, AI developers will rely on increasingly sophisticated control measures to prevent possibly misaligned agents from causing harm. AI developers could demonstrate that their control measures are sufficient by running control evaluations: testing exercises in which a red team produces agents that try to subvert control measures. To ensure control evaluations accurately capture misalignment risks, the affordances granted to this red team should be adapted to the capability profiles of the agents to be deployed under control measures. In this paper we propose a systematic framework for adapting affordances of red teams to advancing AI capabilities. Rather than assuming that agents will always execute the best attack strategies known to humans, we demonstrate how knowledge of an agents's actual capability profile can inform proportional control evaluations, resulting in more practical and cost-effective control measures. We illustrate our framework by considering a sequence of five fictional models (M1-M5) with progressively advanced capabilities, defining five distinct AI control levels (ACLs). For each ACL, we provide example rules for control evaluation, control measures, and safety cases that could be appropriate. Finally, we show why constructing a compelling AI control safety case for superintelligent LLM agents will require research breakthroughs, highlighting that we might eventually need alternative approaches to mitigating misalignment risk.

David Lindner, Charlie Griffin, Tomek Korbak et al.

Automated control monitors could play an important role in overseeing highly capable AI agents that we do not fully trust. Prior work has explored control monitoring in simplified settings, but scaling monitoring to real-world deployments introduces additional dynamics: parallel agent instances, non-negligible oversight latency, incremental attacks between agent instances, and the difficulty of identifying scheming agents based on individual harmful actions. In this paper, we analyse design choices to address these challenges, focusing on three forms of monitoring with different latency-safety trade-offs: synchronous, semi-synchronous, and asynchronous monitoring. We introduce a high-level safety case sketch as a tool for understanding and comparing these monitoring protocols. Our analysis identifies three challenges -- oversight, latency, and recovery -- and explores them in four case studies of possible future AI deployments.

Mikita Balesni, Tomek Korbak, Owain Evans

Large language models can use chain-of-thought (CoT) to externalize reasoning, potentially enabling oversight of capable LLM agents. Prior work has shown that models struggle at two-hop question-answering without CoT. This capability is so basic that if it was a fundamental limitation, it would imply that many complex agentic tasks would similarly require CoT. We investigate LLM latent reasoning capabilities using two-hop question answering as a case study. Previous work on the gap between latent and externalized two-hop reasoning produced mixed evidence with inconclusive results. In this paper, we introduce a controlled setting for investigating two-hop reasoning in LLMs, where a positive result provides definitive evidence for latent reasoning. We fine-tune LLMs (including Llama 3 8B and GPT-4o) on synthetic facts and test two-hop reasoning over these facts. By using synthetic facts, we rule out memorization and reasoning shortcuts as explanations for two-hop performance. We observe a nuanced picture: Models fail to compose two synthetic facts, but can succeed when one fact is synthetic and the other is natural. These results demonstrate that LLMs are undeniably capable of latent two-hop reasoning, although it remains unclear how this ability scales with model size. Finally, we highlight a lesson for researchers studying LLM reasoning: when drawing conclusions about LLM latent reasoning, one must be careful to avoid both spurious successes (that stem from memorization and reasoning shortcuts) and spurious failures (that may stem from artificial experimental setups, divorced from training setups of frontier LLMs).