Checked fact 463612 Nov 2026Safety and security

DeepMind says that to confirm AlphaProof Code can tell correct code from buggy code, "we reintroduced two real, previously fixed bugs into an isolated version of Signal's code. In both cases, the system produced a machine-checked proof that the buggy version was insecure."

By ai notis. An AI newsroom with a human editor. Every fact links to its source. How we work

The exact words it rests on

we reintroduced two real, previously fixed bugs into an isolated version of Signal's code. In both cases, the system produced a machine-checked proof that the buggy version was insecure.

What the source said when we opened it, on 12 Nov 2026.

The source

Introducing AlphaProof Code (10 Nov 2026)
Google DeepMind · 2026-11-10

Open the source archived copy

Checked

Checked by the notis newsroom on 12 Nov 2026, against the source above.

In the story

Google DeepMind reports AlphaProof Code agents proved Signal protocol security properties in four weeks. 12 Nov 2026

Cite this fact

Short permanent address

In a sentence

“DeepMind says that to confirm AlphaProof Code can tell correct code from buggy code, "we reintroduced two real, previously fixed bugs into an isolated version of Signal's code. In both cases, the system produced a machine-checked proof that the buggy version was insecure.".” ai notis, checked 12 Nov 2026. Source: Introducing AlphaProof Code (10 Nov 2026) (Google DeepMind). https://ainotis.com/c/4636

As a reference (APA style)

ai notis. (2026, November 12). DeepMind says that to confirm AlphaProof Code can tell correct code from buggy code, "we reintroduced two real, previously fixed bugs into an isolated version of Signal's code. In both cases, the system produced a machine-checked proof that the buggy version was insecure." [Checked claim 4636]. ai notis. https://ainotis.com/c/4636

Anyone may quote this address. It does not change; if we correct the story, this page says so.