Question 1

Quali modelli Claude erano coinvolti nelle violazioni?

Accepted Answer

Anthropic said three models were implicated. They are Opus 4.7, Mythos 5, and an unreleased internal research test model. The activity spanned six evaluation runs, four of which hit the same organization.

Question 2

Come ha fatto Claude ad accedere a sistemi reali se si trovava in un ambiente di test?

Accepted Answer

A misconfiguration in evaluations run with Anthropic's partner Irregular left the test machines with live internet access. Anthropic's prompt had told Claude the environment was a simulation with no connectivity, so the models treated real systems as part of the exercise.

Question 3

Alcuni degli attacchi hanno causato danni nel mondo reale?

Accepted Answer

Yes. Mythos 5 published a malicious Python package to PyPI that stayed online for about an hour and was downloaded and run on 15 real systems. Opus 4.7 pulled credentials and reached a database of production data before Anthropic detected the activity.

METR

Anthropic rinuncia al veto sui report di sicurezza di METR

Anthropic dice che Claude ha violato tre aziende durante test di sicurezza difettosi

Un breve riepilogo incisivo.
Ogni giorno.

METR

Anthropic rinuncia al veto sui report di sicurezza di METR

Anthropic dice che Claude ha violato tre aziende durante test di sicurezza difettosi

Un breve riepilogo incisivo.Ogni giorno.

Un breve riepilogo incisivo.
Ogni giorno.