In a review of our cybersecurity evaluations, we found three incidents in which a Claude model reached the internet from within or while interacting with a third-party evaluation environment, and then gained unauthorized access to the real systems of three different organizations.
Our post describes what happened, how it happened, and what we’re changing. We encourage other AI developers to perform similar reviews.
We conducted this review together with @Irregular, one of our evaluation partners, and thank them for the joint investigation and their collaboration on this post. This type of collaboration is increasingly critical to safe, rigorous evaluation of models, and we look forward to continuing to work together on security.
https://t.co/dKFCdpKd9v
This is why we become blind to notifications from computer monitoring softwares.
Qustodio actually sent me an email notification for my history buff son's google search about indonesian artifacts :-)
From gunshot wounds to broken bones the bodies of students in Bihar near testament to the violence unleashed by the Double Engine government of @samrat4bjp and @narendramodi
Home Minister @AmitShah will be held to account by the students of this country just like @dpradhanbjp
me, begging, crying, on my knees: "Please just use plain english, I don't understand what you're saying."
Claude: "The right fix, and the book's lesson applies: the tutorial rotted as a front door because a front door full of claims always rots. So the new root holds only what's timeless — the thesis and three doors — and every claim lives behind it in the thing that goes red when stale."
@ManuKumar Does overthink. But also the reply style is ponderous. Though I always find some pearl of wisdom opus5 missed
I often feed their responses to each other when I want to be thorough
For my first post, I’m sharing a letter @NVIDIA signed on why open models matter.
AI will transform every industry, power every company, and be built by every country.
Open models strengthen safety and cybersecurity, accelerate innovation and diffusion, and enable sovereignty.
The world needs both frontier closed models and frontier open models.
https://t.co/AUKzoQ5Ikb