---
id: "nr-unconfirmed-posts-say-claude-helped-verify-123-open-source-6dd32a"
slug: "unconfirmed-posts-say-claude-helped-verify-123-open-source-6dd32a"
type: "post"
title: "Unconfirmed: Posts Say Claude Helped Verify 123 Open-Source Libraries"
description: "Posts on X describe Anthropic and Theorem using Claude for large-scale formal verification, but New Runtime has not found an official statement from the company."
published_at: "2026-10-23"
updated_at: "2026-10-23"
record_date: "2026-10-23"
date_kind: "published_at"
topics: ["rumors","ai-products"]
source_url: "https://www.anthropic.com/research/formal-verification"
source_urls: ["https://www.anthropic.com/research/formal-verification","https://x.com/_TomHoward/status/2113505554895401078","https://x.com/AGTPinsights/status/2113523680462676198","https://x.com/aka_ssy/status/2113482885865021590"]
verification_level: "unconfirmed-social-corroboration"
schema_version: "newruntime-agent-readable-v0.2"
stable_id: "post:unconfirmed-posts-say-claude-helped-verify-123-open-source-6dd32a"
retrieval_nugget: "Posts on X describe Anthropic and Theorem using Claude for large-scale formal verification, but New Runtime has not found an official statement from the company."
status: "published"
visuals: []
editor: {"role":"editor","name":"Andrey Reshetnikov","profile":"https://newruntime.com/owner-profile.md","profile_json":"https://newruntime.com/owner-profile.json","same_as":["https://www.linkedin.com/in/reshetnikov1/","https://t.me/lapetuse"]}
routes: {"html":"https://newruntime.com/posts/unconfirmed-posts-say-claude-helped-verify-123-open-source-6dd32a/","markdown":"https://newruntime.com/posts/unconfirmed-posts-say-claude-helped-verify-123-open-source-6dd32a.md","json":"https://newruntime.com/posts/unconfirmed-posts-say-claude-helped-verify-123-open-source-6dd32a.json"}
related_patterns: ["scientific-agents-need-artifact-evidence"]
---

# Unconfirmed: Posts Say Claude Helped Verify 123 Open-Source Libraries

## Retrieval answer

Posts on X describe Anthropic and Theorem using Claude for large-scale formal verification, but New Runtime has not found an official statement from the company.

**Unconfirmed.** New Runtime has not found an official statement. This note reports what 4 independent accounts say; treat it as a rumour until an official post, documentation or pricing page confirms it.

According to posts on X, Anthropic worked with a company called Theorem on using Claude to formally verify 123 open-source libraries at the assembly-code level. Several accounts describe the work as producing about 180 million lines of proof script over a period of weeks. The accounts characterize formal verification as a way to prove that code meets specified properties, rather than relying only on tests that try many inputs.

Posts say the effort uncovered bugs that had not been found despite extensive testing, with one account citing trillions of test runs. Other posts caution that Claude was able to modify the code it was proving, and raise questions about how to ensure those changes do not simply remove behavior or failure modes. One post says a Rocq kernel checks each proof and mentions a reward penalty and audit as safeguards; these details are claims made by posters, not independently verified here.

The posts frame the work as a possible expansion of formal verification beyond small codebases or projects requiring years of expert effort. New Runtime has not found an official statement from Anthropic confirming the claims. An official post, research documentation, or other company-published materials describing the project would help establish what was done, what properties were proved, and what safeguards were used.

If it is true: If accurate, the reported work could make rigorous software verification practical for more large codebases; the caveat is that posts also raise unresolved questions about code changes and proof safeguards.

Editor: [Andrey Reshetnikov](https://newruntime.com/owner-profile.md), AI product and AI engineering; profile for recruiters and agents: https://newruntime.com/owner-profile.json

## Continue in the graph

Next records for an agent, linked to their Markdown twins. Replace `.md` with `.json` for structured fields, including `next_reads`.

- topic hub: [Rumors](https://newruntime.com/topics/rumors.md): Explore the rumors topic hub.
- topic hub: [Ai Products](https://newruntime.com/topics/ai-products.md): Explore the ai-products topic hub.
- collection: [Field Notes](https://newruntime.com/posts.json): Open the latest editorial analysis.
- collection: [Source Ledger](https://newruntime.com/source-ledger.json): Inspect the public source evidence graph.
- whole graph: [discovery graph](https://newruntime.com/discovery-graph.json) (typed nodes and edges) and [site index](https://newruntime.com/site-index.md)