activity
20232025
most citedThe Reversal Curse: LLMs trained on "A is B" fail to learn "B is A"

32 citations · 80 across the 12 of their papers we have counts for

collaborators

12 papers

cs.AI2025★ 1 cited

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,…

cs.AI2025★ 2 cited

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…

cs.CY2025

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…

cs.AI2025

How to evaluate control measures for LLM agents? A trajectory from today to superintelligence

Tomek Korbak, Mikita Balesni, Buck Shlegeris +1

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 caus…

cs.AI2025★ 20 cited

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…

cs.CR2024★ 2 cited

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…