Tag
This article presents a Tarski-inspired diagonal argument showing that no linear probe on an LLM's embedding space can reliably detect truth, drawing parallels to Gödel's incompleteness and Turing's halting problem. It critiques the linear representation hypothesis for truth in language models.
This paper proposes a probabilistic extension to neuro-symbolic AGI robots using Belnap's typed intensional first-order logic. It introduces global and local symmetry transformations to preserve knowledge and enable real-time decisions, with neural networks computing probability density based on maximum information entropy.
This paper proposes a lattice-theoretic approach to define unbiased canonical set-valued oracles that remain self-consistent even when their outputs are learned and acted upon, addressing the performativity problem in AI prediction.