Reproduce “Physical limits of inference” 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
David H. Wolpert
A framework defines physical 'inference devices' for observation, prediction, and recollection, formalizing 'semantic information content' and deriving universal, law-independent limits on their capabilities. The work demonstrates that no physical device can infallibly infer all possible binary functions, effectively presenting a non-quantum mechanical uncertainty principle for information processing.
Key insights
- Intrinsic, universal limits exist for physical information processing, independent of specific physical laws, chaotic dynamics, or quantum mechanical indeterminism.
- A formalization of 'semantic information content' is essential for analyzing how physical devices acquire meaningful knowledge, distinct from purely syntactic information.
- Analogies between physical inference devices and Turing Machines reveal fundamental computational limits, including an 'inference Halting problem'.
Summary by alphaXiv.
Tip: change arxiv.org to autoarxiv.org in any arXiv abstract link to open the paper here.