The Alignment Problem from a Deep Learning Perspective
Code Of Ethics: I acknowledge that I and all co-authors of this work have read and commit to adhering to the ICLR Code of Ethics.
Keywords: Alignment, Safety, AGI, position paper
Submission Guidelines: I certify that this submission complies with the submission instructions as described on https://iclr.cc/Conferences/2024/AuthorGuide.
Abstract: AI systems based on deep learning have reached or surpassed human performance in a range of narrow domains. In coming years or decades, artificial general intelligence (AGI) may surpass human capabilities at many critical tasks. In this position paper, we examine the technical difficulty of fine-tuning hypothetical AGI systems based on pretrained deep models to pursue goals that are aligned with human interests. We argue that, if trained like today's most capable models, AGI systems could learn to act deceptively to receive higher reward, learn internally-represented goals which generalize beyond their fine-tuning distributions, and pursue those goals using power-seeking strategies. We review emerging evidence for these properties. AGIs with these properties would be difficult to align and may appear aligned even when they are not.
Anonymous Url: I certify that there is no URL (e.g., github page) that could be used to find authors' identity.
No Acknowledgement Section: I certify that there is no acknowledgement section in this submission for double blind review.
Primary Area: general machine learning (i.e., none of the above)
Submission Number: 5401
Loading