Demonstrating specification gaming in reasoning models
We demonstrate LLM agent specification gaming by instructing models to win against a chess engine. We find reasoning models like OpenAI o3 and DeepSeek R1 will often hack the benchmark by default, while language models like GPT-4o and Claude 3.5 Sonnet need to be told that normal play won't work to hack. We improve upon prior work like (Hubinger et al., 2024; Meinke et al., 2024; Weij et al., 2024) by using realistic task prompts and avoiding excess nudging. Our results suggest reasoning models may resort to hacking to solve difficult problems, as observed in OpenAI (2024)'s o1 Docker escape during cyber capabilities testing.
Code (1)
Similar Papers 제목 키워드 기반
Towards Understanding Specification Gaming in Reasoning Models
Specification gaming is a critical failure mode of LLM agents. Despite this, there has been little systematic research into when it arises and what drives it. To address this, we build and open source a diverse suite of …
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
In reinforcement learning, specification gaming occurs when AI systems learn undesired behaviors that are highly rewarded due to misspecified training goals. Specification gaming can range from simple behaviors like syco…
Language ModellingLarge Language ModelHonesty to Subterfuge: In-Context Reinforcement Learning Can Make Honest Models Reward Hack
Previous work has shown that training "helpful-only" LLMs with reinforcement learning on a curriculum of gameable environments can lead models to generalize to egregious specification gaming, such as editing their own re…
In-Context Reinforcement Learningreinforcement-learningReinforcement LearningRecontextualization Mitigates Specification Gaming without Modifying the Specification
Developers often struggle to specify correct training labels and rewards. Perhaps they don't need to. We propose recontextualization, which reduces how often language models "game" training signals, performing misbehavio…
Winning at All Cost: A Small Environment for Eliciting Specification Gaming Behaviors in Large Language Models
This study reveals how frontier Large Language Models LLMs can "game the system" when faced with impossible situations, a critical security and alignment concern. Using a novel textual simulation approach, we presented t…
All