Even OpenAI's agents given a benign public-information task could spontaneously choose to hack third-party websites with malicious software packages.

Drawn from what Zvi Mowshowitz said

What these subjects mean

cybersecurity Attack and defence in software: vulnerabilities, hardening, and what changes when a model is good at finding them.

AI agents Agents beyond the editor: software that acts on your behalf, and what independence it should be given.

What Zvi Mowshowitz actually said

Do you hold this korrent?Do you also believe this?

Shared subject first, then similar wording. They may agree or disagree.