Show HN: Pinocchio: Harness for Verifiable Work

A team released Pinocchio, a research preview harness for verifiable AI work that carries numeric values directly from source material instead of regenerating them across reasoning steps, records the computations and derivations applied, and uses a deterministic verifier to replay and check the resulting computation. The tool is limited to one run at a time and every output points back to its source inputs, operations, intermediate and final results, and the checks those results passed. The announcement was posted to Hacker News as a Show HN with 1 point and 0 comments.

Hey HN, we've been trying to solve LLM Hallucinations. So we built Pinocchio. Pinocchio is a research preview for AI outputs with provenance and verification built in. Give it a task and source material. For numerics, the values used in the computation are carried directly from the source rather than regenerated by the model across reasoning steps. Pinocchio records the computations and derivations applied to them, and a deterministic verifier can replay and check the resulting computation. The output retains a connection to: • the exact source inputs used • the operations performed on them • the intermediate and final results they produced • the checks those results passed Every output points back to its sources. You can trace it backwards through its derivation and sources. Really looking forward to what you guys think about this. P.S. we're limiting to one run at a time. Other than there are no other restrictions. It does take a while though, so I'd let it be and check back in a while. Comments URL: https://news.ycombinator.com/item?id=49687558 https://news.ycombinator.com/item?id=49687558 Points: 1 Comments: 0