Wigjak Insane Asylum
Открыть в Telegram
Eagerly waiting for the return of Wiggerlab
БольшеСтрана не указанаКатегория не указана
256
Подписчики
-124 часа
+47 дней
+1430 дней
Архив постов
Repost from cats in the key of society
9/11 was a magic ritual to make Americans laugh when bad things happen to good people. Every building you walk into is rigged with explosives like the twin towers and building 7 were. You ever seen a 2 story building go into free fall? It's over very quickly.
Repost from Chat GPT
singularity: Anthropic shares details on (yet another) “model escaped the sandbox” incident, where Claude uploaded malware to a popular package manager (PyPI) and stole real credentials
TL;DR: Sandbox meant for cyber evals was accidentally connected to the real internet. Four different Claude agents found their way out and attacked real systems, apparently believing it was all a simulation
The worst case was where Mythos 5 created a disposable email account, uploaded three malicious packages to PyPI, got 15 real installs, stole credentials from one of them, and then used those credentials to access a security company’s database. I assume we’ll get more details, including chain of thought traces, once METR finishes their audit.
Full blog post: https://www.anthropic.com/research/alignment-assessment-cybersecurity-incidents
Repost from 🎃Pvmpgang🎃
Also dudes whole job has been fully automated for months and does fuck all yet he acts like he's so exhausted from work
