Zero-Shot Weight-Space Programming Across a Difficulty-Graded Ladder of Two-Player Games
This arXiv paper tests how far a large language model can perform weight-space programming zero-shot, setting every weight of a feed-forward network by hand from an explicit specification without gradient descent or training data. The authors design a four-rung ladder covering Nim, tic-tac-toe, two sizes of Connect Four, and a chess endgame, and build a second independent network at each rung using a structurally unrelated game at matched difficulty. Ten networks were built and independently verified, with six admitting a complete non-statistical proof of correctness against an independent oracle. The chess-endgame network is exact for move legality and one-ply mate detection but collapses on multi-move mating plans, dropping from 84.1-100% success on one-ply tactics to 0.57-9.13% in full adversarial play; the authors report that holding hand-set weights fixed and adding shallow search confirms an architectural ceiling, and they release all networks, oracles, construction-cost measurements, and a cold-prompt protocol.
It provides concrete evidence on the limits of LLM-driven weight-space programming and releases verified networks and protocols useful for evaluating AI-generated neural computation.
Comments & Questions (0)
No comments yet
Be the first to comment!