Search Results for author:
Found 3 papers, 1 papers with code
Poser: Unmasking Alignment Faking LLMs by Manipulating Their Internals
Like a criminal under investigation, Large Language Models (LLMs) might pretend to be aligned while evaluated and misbehave when they have a good opportunity.
Safety Cases: How to Justify the Safety of Advanced AI Systems
To prepare for these decisions, we investigate how developers could make a 'safety case,' which is a structured rationale that AI systems are unlikely to cause a catastrophe.
Generalization Analogies: A Testbed for Generalizing AI Oversight to Hard-To-Measure Domains
As AI systems become more intelligent and their behavior becomes more challenging to assess, they may learn to game the flaws of human feedback instead of genuinely striving to follow instructions; however, this risk can be mitigated by controlling how LLMs generalize human feedback to situations where it is unreliable.
