Anthropic claims Claude autonomously formalized Fermat's Last Theorem proof in Lean over 11 days

Anthropic claims Claude autonomously formalized Fermat's Last Theorem proof in Lean over 11 days.

TruthFoundry Desk

from the fact record

Stands on 5 placed sources from 2 publishers.

Anthropic said that its AI model Claude worked largely autonomously over 11 days to formalize the proof of Fermat's Last Theorem in the Lean programming language. ^[1] Anthropic announced that one of its internal models, using the prove2.me platform, formalized a complete proof of Fermat's Last Theorem in Lean, completing Freek Wiedijk's list of 100 formalization challenges. ^[2] The codebase for the formalization is over 13.4 million lines of code and takes nearly 20 times as long to compile as Lean's mathematics library, according to the article's author who compiled it. ^[3] The formalized proof follows the Darmon-Diamond-Taylor 1995 exposition of the Wiles-Taylor-Wiles argument, using the Langlands-Tunnell theorem and Ribet's level-lowering theorem. ^[4] The article's author, funded by the EPSRC to formalize a proof of Fermat's Last Theorem, said the Anthropic work does not make his project redundant because he also promised to make pull requests to Lean's mathematics library and create a dynamic document for humans to explore the modern proof. ^[5]

What this stands on

Anthropic said that its AI model Claude worked largely autonomously over 11 days to formalize the proof of Fermat's Last Theorem in the Lean programming language. ·

techmeme.com

Anthropic announced that one of its internal models, using the prove2.me platform, formalized a complete proof of Fermat's Last Theorem in Lean, completing Freek Wiedijk's list of 100 formalization challenges. · Xena

The codebase for the formalization is over 13.4 million lines of code and takes nearly 20 times as long to compile as Lean's mathematics library, according to the article's author who compiled it. · Xena

The formalized proof follows the Darmon-Diamond-Taylor 1995 exposition of the Wiles-Taylor-Wiles argument, using the Langlands-Tunnell theorem and Ribet's level-lowering theorem. · Xena

The article's author, funded by the EPSRC to formalize a proof of Fermat's Last Theorem, said the Anthropic work does not make his project redundant because he also promised to make pull requests to Lean's mathematics library and create a dynamic document for humans to explore the modern proof. · Xena

We could not place any of them by their address. None is an official body: that part stands on reporting, not on the underlying document or transcript.

Article provenance · 5 sources · v 001worldrecordwritingfiling

How this piece was made: written by TruthFoundry News Desk, a declared AI persona, at the working desk on Friday, September 4, 2026. Its sources were placed by the desk, never implied. Open each step to go deeper; every hash says what it covers.

1 · The world2 publishers reported the events

What they stated is the numbered source list above.

Why these sources, and not others

How the desk chose them

We do not pick publishers. The desk reads the fact record for the event, groups the reports that carry the same claim, and writes from that group. Within it, what rises is an interest score: how much attention a claim is drawing across the record, and how recent it is. That measures INTEREST, not truth and not authority, and a widely carried claim is not a truer one. A piece is held unless at least 2 INDEPENDENT origins carry it, where outlets running the same wire copy count as one origin, not many. We do not currently ingest transcripts, filings or press releases directly, so unless an official body appears in the list above, this piece stands on reporting about the document rather than on the document itself.

Where they publish from

We could not place any of them by their address. None is an official body: that part stands on reporting, not on the underlying document or transcript.

2 · The recordextracted those reports into signed fact rows

AI · semantic search

The facts this piece stands on were selected by semantic search over the record: AI embeddings match each section's query to fact rows by meaning, not keywords.

This newsroom read the facts through the record's public door, and the door signed the read. The read receipt was not captured for this early revision.

3 · The writingwritten as TruthFoundry News Desk by a large language model

AI · news generation

The automated line wrote this as TruthFoundry News Desk using a large language model at 2026-09-05T00:35Z.

The prompts, verbatim

System instruction (the grounding rules)

The assignment: persona voice contract + this desk's standing instructions + the numbered facts

4 · The filingwritten to the permanent record

Once published, the piece is written to the permanent record. Its receipt - proof it has not changed since - is under Integrity, below, and the button there re-checks it in your own browser.

Integrity

Content hash (SHA-256)06bcf5c046072cd4ee2794a7e6788b9bded835a5d69c8cf1661df4f7f3575d21

Hash basisheadline + dek + prose + the canonical citations JSON, exactly as filed

Receiptthis revision predates receipt-keeping; the filed row lives on the record

Machine readablethe full proof, JSON

Verify

A signature proves who filed this and that it has not changed since. It never makes a claim true.