Reproduce “Prompting Complexity: Shortest Prompts for Texts and Behaviors in LLMs” on OpenResearch
Turn your favorite coding agents into research agents that review literature, develop hypotheses, and run experiments.
Universal app for Apple silicon and Intel. Requires macOS 11 or later.
About this paper
Adrian Cosma
The authors define prompting complexity as the shortest plausible prompt, measured in tokens, that makes a fixed language model produce a target text under a specified interface and deterministic decoding. They extend it to approximate outputs and accepted behaviors. The framework is computable in principle but exhaustive search is infeasible; it measures model-relative access, not intrinsic task difficulty or compression.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.