When asked to find loopholes (in laws, rules, policies, wishes, etc.)—do LLMs find similar loopholes to humans? Are they from a narrower distribution? To different LLMs find similar loopholes? Are there loopholes that LLMs notice but aren't willing to declare?
h/t Tomer Ullman for getting me hooked on thinking about loopholes
If you are inspired by this idea, you can reach out to the authors for collaboration or cite it:
@misc{holtzman-llm-loopholes-vs-2026,
author = {Holtzman, Ari},
title = {LLM Loopholes vs. Human Loopholes},
year = {2026},
url = {https://hypogenic.ai/ideahub/idea/65jfKQzLpxQUSru9s3Pk}
}Please sign in to comment on this idea.
No comments yet. Be the first to share your thoughts!