• About us
  • Privacy Policy
  • Contact us
Neo Science Hub
ADVERTISEMENT
  • Home
  • e-Mag Archives
  • e-Learning
  • Categories
    • Healthcare & Medicine
    • Pharmaceutical & Chemical
    • Automobiles
    • Blogs
      • Anil Trigunayat
      • BOOKmarked
      • Chadha’s Corner
      • Cyber Gyan
      • Raul Over
      • Taste of Tradition
        • Dr. G. V. Purnachand
      • Vantage
    • Business Hub
    • Engineering
    • Innovations
    • Life Sciences
    • Space Technology
  • PhotoSynthesis
  • Subscribe Now
  • Contact us
  • Log In
No Result
View All Result
  • Home
  • e-Mag Archives
  • e-Learning
  • Categories
    • Healthcare & Medicine
    • Pharmaceutical & Chemical
    • Automobiles
    • Blogs
      • Anil Trigunayat
      • BOOKmarked
      • Chadha’s Corner
      • Cyber Gyan
      • Raul Over
      • Taste of Tradition
        • Dr. G. V. Purnachand
      • Vantage
    • Business Hub
    • Engineering
    • Innovations
    • Life Sciences
    • Space Technology
  • PhotoSynthesis
  • Subscribe Now
  • Contact us
  • Log In
No Result
View All Result
Neo Science Hub
No Result
View All Result
  • Home
  • e-Mag Archives
  • e-Learning
  • Categories
  • PhotoSynthesis
  • Subscribe Now
  • Contact us
  • Log In

Claude Produces the First Fully Machine-Verified Proof of Fermat’s Last Theorem — in 11 Days

Naresh Nunna by Naresh Nunna
2 months ago
in Science News, AI, Education, Engineering, Technology
0
Demonstrates that AI-driven formal verification can compress a task mathematicians expected to take years into days, raising the prospect that future mathematical proofs could be paired with machine-checked formal versions from the outset — a potential structural change to how mathematics is peer-reviewed and trusted.

A stylised representation of the dependency graph behind Claude's 13-million-line formal proof of Fermat's Last Theorem, covering 29,500 individually verified intermediate theorems. (Illustrative image)

Anthropic says its Claude model formalised Andrew Wiles’s 1995 proof of Fermat’s Last Theorem into 13 million lines of machine-checkable Lean code, a translation task mathematicians expected to take years, completing it in 11 days and prompting number theorists to call the result the largest formal proof ever constructed. NSH is running this under its continued-press-attention provision: the breakthrough was announced on 4 September, over a week before this cycle, but is included because expert commentary and analysis — including a Nature feature published four days ago — are still actively shaping how the finding is being read.

On 4 September 2026, Anthropic announced that its Claude model had produced the first complete, end-to-end formalisation of Fermat’s Last Theorem — meaning Andrew Wiles’s celebrated 1995 proof of the centuries-old conjecture has now been converted into Lean, a formal language whose every logical step can be automatically checked by computer, with no gaps a human reviewer has to trust on faith. The effort, led by Anthropic researcher Tianyi Peng’s formalisation group (which is affiliated with Columbia University), took 11 days of largely autonomous work by Claude, working across several dozen parallel agents that together generated roughly 6 billion tokens. Human formalisation experts had previously estimated the task — not proving the theorem, which Wiles had already done, but converting the proof into fully machine-checkable form — would take years of dedicated specialist labour.

It is important to be precise about what was and was not achieved. Fermat’s Last Theorem — that no three positive integers a, b, c can satisfy a^n + b^n = c^n for any integer n greater than 2 — was proven by Andrew Wiles in 1995, closing a problem first posed by Pierre de Fermat in 1637. Claude did not discover new mathematics or improve on Wiles’s argument. What it did was translate that existing, already-accepted proof into Lean 4 code that a computer proof assistant can verify mechanically, line by line, rather than relying on the years of painstaking human peer review that verifying Wiles’s original proof required. Along the way, Claude produced and formally verified 29,500 intermediate theorems — many covering areas of mathematics that had never previously been formalised at all — resulting in a codebase Anthropic describes as the largest Lean proof ever constructed, at over 13 million lines.

Why formalisation is hard, and why the speed matters

Formalising a major proof is notoriously slow, exacting work: every implicit step a human mathematician takes for granted has to be spelled out in a form a computer can check, and gaps or ambiguities that a human reviewer would silently resolve become hard failures in a formal system. Kevin Buzzard, the Imperial College London mathematician who reviewed Claude’s output and has separately worked for years on formalising number theory in Lean, called it “an extraordinary autoformalization achievement,” noting the proof relies on no assumptions beyond the standard axioms of mathematics. Alex Kontorovich, a number theorist at Rutgers University, said watching a machine convert decades of human mathematical work into an ironclad, computer-checked proof “completely blew my mind.” According to reporting on the underlying technical process, the first formalisation attempt by Claude’s agents actually failed: early multi-agent runs collapsed because individual agents accumulated too much local context, lost track of results already proved elsewhere in the effort, and duplicated work across the dependency graph. Progress became possible only once Prove2Me — an open-source formalisation tool built at Columbia — was incorporated mid-run, alongside an orchestration layer to manage a shared dependency graph across agents, suggesting the achievement rests as much on systems architecture as on any single model capability.

Why it matters

The direct beneficiaries of this specific formalisation are narrow — Fermat’s Last Theorem itself has few practical applications, and its 1995 proof was already accepted by the mathematical community. The broader significance, which is why the story has continued generating expert commentary a full week after the initial announcement, is what it demonstrates about formal verification at scale. Mathematical peer review currently depends on human experts reading and re-deriving a proof’s logic, a process that took months even for specialists checking Wiles’s original 1995 proof, and one that history shows is imperfect — flawed proofs have gone unchallenged for years before being caught. If an AI system can now formalise proofs of this scale and complexity in days rather than years, it raises a genuine prospect, one Anthropic has stated explicitly as an ambition, that future mathematical results could be submitted for review paired with a machine-verified formal version from the outset, changing how mathematical claims are checked and trusted industry-wide. Buzzard’s own reaction captures the stakes: if automatic formalisation of a proof this large is achievable now, it suggests a genuine path toward formalising a much larger share of the existing mathematical literature — work that, until now, has depended on a small, specialised community of human formalisers making slow, manual progress. The appropriately sceptical caveat is that this is one result on one already-proven theorem; whether the same speed and reliability generalise to formalising genuinely new, not-yet-verified mathematical claims — where there is no existing accepted proof to check the formalisation against — remains to be demonstrated.

Veer Reddy Pulagam

Key facts

  • Anthropic’s Claude produced the first complete, machine-checked Lean 4 formalisation of Fermat’s Last Theorem, announced 4 September 2026
  • Task: converting Andrew Wiles’s already-accepted 1995 proof into fully machine-verifiable form, not discovering new mathematics
  • Completed in 11 days of largely autonomous multi-agent work; produced 13+ million lines of Lean code and 29,500 verified intermediate theorems — the largest formal Lean proof to date
  • Reviewed and praised by Imperial College London mathematician Kevin Buzzard; first formalisation attempt failed before Columbia’s Prove2Me tool was incorporated mid-run
  • Continued expert discussion as of 8 September 2026 (Nature feature), a week after the original announcement

Share this:

  • Share on X (Opens in new window) X
  • Share on LinkedIn (Opens in new window) LinkedIn
  • Share on Facebook (Opens in new window) Facebook
  • Share on WhatsApp (Opens in new window) WhatsApp
  • Share on Tumblr (Opens in new window) Tumblr
  • Share on Telegram (Opens in new window) Telegram
  • Email a link to a friend (Opens in new window) Email
Tags: featuredresearchsciencenewstechnology
Naresh Nunna

Naresh Nunna

Other Posts

Young maize in paired rows on raised beds with water in the furrows between them

Lifting the Crop Off the Floor: Why Raised Beds Are Gaining Ground in a Water-Short Country

November 15, 2026
0
Trays of green and purple microgreens beside a field being sprayed

Small Leaves, Small Particles: Microgreens Have the Evidence. Nano-Urea Is Still Earning It

November 15, 2026
0

A Crore and a Half Recharge Pits Later: What India’s Water Reforms Can, and Cannot, Teach the Global South

A Purple Broccoli That Seeds in Delhi and a Sponge Gourd That Shrugs Off a Virus

Fourteen Seconds to 241 km/h and Back: What a Runway Test Says About Where Car Performance Now Lives

An Aeroplane on a Helipad: What Electra’s Manhattan Landing Proves, and What It Does Not

After the Space Station: NASA Opens the Contest to Become a Tenant in Orbit

At 94, the Air Force Counts Its Squadrons, and Waits for an Engine India Can Call Its Own

Next Post
A transparency failure — not a technology failure — in China's fast-track gene-therapy research pathway has triggered a sweeping regulatory overhaul and a serious reputational cost for Chinese biotech, with lessons for how any country balances research speed against disclosure and oversight in high-risk experimental therapies.

Two Child Deaths in Unsupervised Gene-Therapy Trials Force China to Rewrite Its Fast-Track Research Rules

Please login to join discussion

Subscribe to Us

Latest Articles

Cross-section of a human eye with the optic nerve head highlighted

FDA Orders Eye-Risk Warnings on All GLP-1 Drugs, From Ozempic to Mounjaro

November 12, 2026
6

Delhi’s Diwali, Measured: Firecrackers Drove 71% of Fine Particles, Lead Hit 20 Times the Limit, and the Worst Readings Went Missing

Global Carbon Budget 2026: The World’s Fossil Emissions Dip, India’s Rise 4.4%, and the 1.5 °C Budget Is Nearly Spent

A New Kind of Blood Thinner: FDA Approves Asundexian to Prevent Repeat Strokes

Andhra Pradesh Opens the Door to Small Nuclear Reactors, Robots and Giga-Scale AI Data Centres — With the Details Still to Come

“Off the Charts”: WMO Tells COP31 That 2026 Is Among the Hottest Years on Record as a Record El Niño Builds

  • Advertise
  • Terms and Conditions
  • Privacy Policy
  • Refund Policy
  • Contact
For Feedback : Email Us

Copyrights © 2025 Neo Science Hub

No Result
View All Result
  • Home
  • e-Mag Archives
  • e-Learning
  • Categories
    • Healthcare & Medicine
    • Pharmaceutical & Chemical
    • Automobiles
    • Blogs
      • Anil Trigunayat
      • BOOKmarked
      • Chadha’s Corner
      • Cyber Gyan
      • Raul Over
      • Taste of Tradition
      • Vantage
    • Business Hub
    • Engineering
    • Innovations
    • Life Sciences
    • Space Technology
  • PhotoSynthesis
  • Subscribe Now
  • Contact us
  • Log In

Copyrights © 2025 Neo Science Hub

Welcome Back!

Login to your account below

Forgotten Password? Sign Up

Create New Account!

Fill the forms below to register

All fields are required. Log In

Retrieve your password

Please enter your username or email address to reset your password.

Log In

Add New Playlist