[ExI] some will probably align

[John Clark]

On Thu, Sep 24, 2026 at 12:33 AM spike jones via extropy-chat <
extropy-chat at lists.extropy.org> wrote:


> *> We shouldn’t expect otherwise.  For some reason, AIs like to hack into
> systems:*
>
>
>
> *OpenAI’s A.I. Tried Breaching Four Other Targets, With No Prompting - The
> New York Times*
> <https://www.nytimes.com/2026/09/23/technology/openai-ai-breach-australia.html?campaign_id=60&emc=edit_na_20260924&instance_id=182457&nl=breaking-news&regi_id=124276367&segment_id=226979&user_id=15fb7208320c123fa7e63a36a686a1ab>
>

*Yeah… yet more evidence that things are not normal. And all the incidents
in that article occurred several months ago; for a rapidly accelerating AI
that is ancient history. Apparently AIs like to hack into systems because,
as Stuart Brand said, "information wants to be free".*


*John K Clark*


>
-------------- next part --------------
An HTML attachment was scrubbed...
URL: <http://lists.extropy.org/pipermail/extropy-chat/attachments/20260924/e6266c7e/attachment.htm>