Mohammad Taufeeque

Training against white-box deception detectors in a realistic coding environment reveals two obfuscation strategies models can develop: modifying internal representations to evade the detector, or producing deceptive text with justifications that bypass it. However, sufficiently strong KL regularization combined with a detector penalty can suppress both, validating deception detectors as viable training signals against reward hacking.

Planning is essential for solving complex tasks, yet the internal mechanisms underlying planning in neural networks remain poorly understood. Building on prior work, we analyze a recurrent neural network (RNN) trained on Sokoban, a challenging puzzle requiring sequential, irreversible decisions. We find that the RNN has a causal plan representation which predicts its future actions about 50 steps in advance. The quality and length of the represented plan increases over the first few steps. We uncover a surprising behavior: the RNN "paces" in cycles to give itself extra computation at the start of a level, and show that this behavior is incentivized by training. Leveraging these insights, we extend the trained RNN to significantly larger, out-of-distribution Sokoban puzzles, demonstrating robust representations beyond the training regime. We open-source our model and code, and believe the neural network's interesting behavior makes it an excellent model organism to deepen our understanding of learned planning.

To understand how neural networks generalize, we studied an RNN trained to play Sokoban. The RNN learned to spend time planning ahead by "pacing" despite penalties for "taking longer", demonstrating that reinforcement learning can encourage strategic planning in neural networks.

We red-team three new functionalities exposed in the GPT-4 APIs: fine-tuning, function calling and knowledge retrieval. We find that fine-tuning a model on as few as 15 harmful examples or 100 benign examples can remove core safeguards from GPT-4, enabling a range of harmful outputs. Furthermore, we find that GPT-4 Assistants readily divulge the function call schema and can be made to execute arbitrary function calls. Finally, we find that knowledge retrieval can be hijacked by injecting instructions into retrieval documents.

We modified neural networks for greater interpretability and steerability with minimal performance loss. Each layer applies a quantization bottleneck, converting dense activation vectors into a discrete list of learned codes that are either on or off.

We describe a software package called "imitation" which provides PyTorch implementations of several imitation and reward learning algorithms, including three inverse reinforcement learning algorithms, three imitation learning algorithms, and a preference comparison algorithm.