Search Results for author:
Found 5 papers, 4 papers with code
Alignment faking in large language models
Explaining this gap, in almost all cases where the model complies with a harmful query from a free user, we observe explicit alignment-faking reasoning, with the model stating it is strategically answering harmful queries in training to preserve its preferred harmlessness behavior out of training.
Sycophancy to Subterfuge: Investigating Reward-Tampering in Large Language Models
We construct a curriculum of increasingly sophisticated gameable environments and find that training on early-curriculum environments leads to more specification gaming on remaining environments.
Sleeper Agents: Training Deceptive LLMs that Persist Through Safety Training
We find that such backdoor behavior can be made persistent, so that it is not removed by standard safety training techniques, including supervised fine-tuning, reinforcement learning, and adversarial training (eliciting unsafe behavior and then training to remove it).
Understanding and Controlling a Maze-Solving Policy Network
To understand the goals and goal representations of AI systems, we carefully study a pretrained reinforcement learning policy that solves mazes by navigating to a range of target squares.
Steering Language Models With Activation Engineering
To reduce this gap, we introduce activation engineering: the inference-time modification of activations in order to control (or steer) model outputs.
