59 citations · 72 across the 5 of their papers we have counts for
6 papers
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…
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…
Towards Implicit Bias Detection and Mitigation in Multi-Agent LLM Interactions
Angana Borah, Rada Mihalcea
As Large Language Models (LLMs) continue to evolve, they are increasingly being employed in numerous studies to simulate societies and execute diverse social tasks. However, LLMs a…
Taken out of context: On measuring situational awareness in LLMs
Lukas Berglund, Asa Cooper Stickland, Mikita Balesni +5
We aim to better understand the emergence of `situational awareness' in large language models (LLMs). A model is situationally aware if it's aware that it's a model and can recogni…
Model evaluation for extreme risks
Toby Shevlane, Sebastian Farquhar, Ben Garfinkel +18
Current approaches to building general-purpose AI systems tend to produce systems with both beneficial and harmful capabilities. Further progress in AI development could lead to ca…
GPT-4 Technical Report
OpenAI, Josh Achiam, Steven Adler +278
We report the development of GPT-4, a large-scale, multimodal model which can accept image and text inputs and produce text outputs. While less capable than humans in many real-wor…