72 citations · 112 across the 14 of their papers we have counts for
14 papers
Constitutional Black-Box Monitoring for Scheming in LLM Agents
Simon Storf, Rich Barton-Cooper, James Peters-Gill +1
Safe deployment of Large Language Model (LLM) agents in autonomous settings requires reliable oversight mechanisms. A central challenge is detecting scheming, where agents covertly…
Stress Testing Deliberative Alignment for Anti-Scheming Training
Bronson Schoen, Evgenia Nitishinskaya, Mikita Balesni +16
Highly capable AI systems could secretly pursue misaligned goals -- what we call "scheming". Because a scheming AI would deliberately try to hide its misaligned goals and actions,…
Chain of Thought Monitorability: A New and Fragile Opportunity for AI Safety
Tomek Korbak, Mikita Balesni, Elizabeth Barnes +38
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 A…
AI Behind Closed Doors: a Primer on The Governance of Internal Deployment
Charlotte Stix, Matteo Pistillo, Girish Sastry +6
The most advanced future AI systems will first be deployed inside the frontier AI companies developing them. According to these companies and independent experts, AI systems may re…
Forecasting Frontier Language Model Agent Capabilities
Govind Pimpale, Axel Højmark, Jérémy Scheurer +1
As Language Models (LMs) increasingly operate as autonomous agents, accurately forecasting their capabilities becomes crucial for societal preparedness. We evaluate six forecasting…
Detecting Strategic Deception Using Linear Probes
Nicholas Goldowsky-Dill, Bilal Chughtai, Stefan Heimersheim +1
AI models might use deceptive strategies as part of scheming or misaligned behaviour. Monitoring outputs alone is insufficient, since the AI might produce seemingly benign outputs…
Frontier Models are Capable of In-context Scheming
Alexander Meinke, Bronson Schoen, Jérémy Scheurer +3
Frontier models are increasingly trained and deployed as autonomous agent. One safety concern is that AI agents might covertly pursue misaligned goals, hiding their true capabiliti…
Towards evaluations-based safety cases for AI scheming
Mikita Balesni, Marius Hobbhahn, David Lindner +13
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 sc…
Analyzing Probabilistic Methods for Evaluating Agent Capabilities
Axel Højmark, Govind Pimpale, Arjun Panickssery +2
To mitigate risks from AI systems, we need to assess their capabilities accurately. This is especially difficult in cases where capabilities are only rarely displayed. Phuong et al…
Me, Myself, and AI: The Situational Awareness Dataset (SAD) for LLMs
Rudolf Laine, Bilal Chughtai, Jan Betley +6
AI assistants such as ChatGPT are trained to respond to users by saying, "I am a large language model". This raises questions. Do such models know that they are LLMs and reliably a…
The Local Interaction Basis: Identifying Computationally-Relevant and Sparsely Interacting Features in Neural Networks
Lucius Bushnaq, Stefan Heimersheim, Nicholas Goldowsky-Dill +7
Mechanistic interpretability aims to understand the behavior of neural networks by reverse-engineering their internal computations. However, current methods struggle to find clear…
Using Degeneracy in the Loss Landscape for Mechanistic Interpretability
Lucius Bushnaq, Jake Mendel, Stefan Heimersheim +5
Mechanistic Interpretability aims to reverse engineer the algorithms implemented by neural networks by studying their weights and activations. An obstacle to reverse engineering ne…
Black-Box Access is Insufficient for Rigorous AI Audits
Stephen Casper, Carson Ezell, Charlotte Siegmann +18
External audits of AI systems are increasingly recognized as a key mechanism for AI governance. The effectiveness of an audit, however, depends on the degree of access granted to a…
Large Language Models can Strategically Deceive their Users when Put Under Pressure
Jérémy Scheurer, Mikita Balesni, Marius Hobbhahn
We demonstrate a situation in which Large Language Models, trained to be helpful, harmless, and honest, can display misaligned behavior and strategically deceive their users about…