Telling the model its RAM and wall-time budget takes correct-and-in-budget code from 0/5 to 4/5.

Claude Opus 5, GPT-5.6-Sol and Gemini 3.7 Flash generated code for a high-dimensional pairwise distance task either from the task alone or with an explicit 128 MB RAM and 10.0 s wall-time contract in the prompt (arXiv 2609.05232). Contract disclosure cut peak process memory in 13 of 14 index-aligned comparisons and made execution up to 3.1x faster. At a tighter 96 MB contract, correct-and-within-budget outcomes went from 0/5, 1/5 and 0/5 to 4/5, 5/5 and 3/5. The models responded structurally, adopting bounded blocking, float32 retention, upper-triangle traversal and memory-mapped buffers. One line in the prompt.