A Neurosymbolic Approach to Natural Language Formalization and Verification · HackerPapers discussions

A Neurosymbolic Approach to Natural Language Formalization and Verification — mentioned by wyattbenno

Fri, 06 Mar 2026 14:04:03 GMT

Hi, AI Agents Can Move Money. Lobstar Wilde Proved They Can Lose It Too... So we made: (ARc + ZK) Neurosymbolic formal reasoning w/ zero knowledge proofs for cryptographically secure agentic guardrails. Our approach has two essential properties for agentic commerce: (1) succinct proofs and (2) optional privacy. The core idea is from the Automated Reasoning Checks (ARc) paper (https://arxiv.org/pdf/2511.09008) which converts natural language policies into SMT-LIB constraints and checks agent actions against an SMT solver rather than an LLM judge. The solver proofs are not succinctly verifiable…

Paper and discussion history. A mention is not an endorsement.

A Neurosymbolic Approach to Natural Language Formalization and Verification — mentioned by logicprog

Tue, 10 Feb 2026 23:00:02 GMT

I think framing it as a site for people that are positive about AI is probably the wrong way to go, but around it kf you don't want just a bunch of AI psychosis posts and nothing else. I think it would be better if, instead of being defined in terms of being "positive" about AI (in the sense of saying that everything to do with AI is all great and rosy and awesome, and thinking every new AI thing is the next big thing, and praising every vibe-coded piece of slop), the focus was explicitly on having mature, software engineering-focused discussions of how to actually understand, make, and use…

Paper and discussion history. A mention is not an endorsement.