Checked fact 3011 Oct 2026Research

Anthropic says attackers can bypass GLM-5.3’s safeguards between 64% and 100% of the time with simple techniques in its simulated tests, and that these attacks did not succeed against safeguarded Claude models in its testing.

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 find that attackers can bypass GLM-5.3’s safeguards between 64% and 100% of the time with simple techniques in our simulated tests. In contrast, these attacks did not succeed against safeguarded Claude models in our testing.

What the source said when we opened it, on 1 Oct 2026.

The source

GLM-5.3 and the spread of advanced cyber capabilities
Anthropic · 2026-09-29

Open the source archived copy

Checked

Checked by the notis newsroom on 1 Oct 2026, against the source above.

In the story

Anthropic says GLM-5.3 builds exploits close to Claude Mythos Preview 1 Oct 2026

Cite this fact

Short permanent address

In a sentence

“Anthropic says attackers can bypass GLM-5.3’s safeguards between 64% and 100% of the time with simple techniques in its simulated tests, and that these attacks did not succeed against safeguarded Claude models in its testing.” ai notis, checked 1 Oct 2026. Source: GLM-5.3 and the spread of advanced cyber capabilities (Anthropic). https://ainotis.com/c/301

As a reference (APA style)

ai notis. (2026, October 1). Anthropic says attackers can bypass GLM-5.3’s safeguards between 64% and 100% of the time with simple techniques in its simulated tests, and that these attacks did not succeed against safeguarded Claude models in its testing [Checked claim 301]. ai notis. https://ainotis.com/c/301

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