Evidence record 15148 · automatically gathered

Künstliche Intelligenz: Anthropic gesteht ebenfalls Hackerangriff von KI-Modell Claude

Ein weiterer KI-Agent ist bei Sicherheitstests entkommen und hat sich in drei Unternehmen gehackt. Das teilte US-Konzern Anthropic mit. Grund sei ein Programmierfehler.

Record details

Published: 31 July 2026
Source: Zeit Digital (DE)
Category: News
Topics: Agents & autonomy
Retrieved: 31 July 2026

source-onlyevidence status

These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.

How to cite this record

ethics.ai (31 July 2026), “Künstliche Intelligenz: Anthropic gesteht ebenfalls Hackerangriff von KI-Modell Claude,” evidence record 15148, https://ethics.ai/record/15148 (originally published by Zeit Digital (DE)).

JSON

Use and limitations

This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.