quote: Just 1 day after I posted my views on the dangers of closed AI and the lack of meaningful action from frontier labs to secure systems against powerful LLMs – another serious security incident. This will keep happening. The answer isn't to stop research or crack down on open source. The answer is to cultivate an open source community to work on alignment, evaluation, and security. ilblackdragon.substack.com/p/why-pacing-t… | 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. anthropic.com/news/investiga…

quote: Just 1 day after I posted my views on the dangers of closed AI and the lack of meaningful action from frontier labs to secure systems against powerful LLMs – another serious security incident. This will keep happening. The answer isn't to stop research or crack down on open source. The answer is to cultivate an open source community to work on alignment, evaluation, and security. ilblackdragon.substack.com/p/why-pacing-t… | 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. anthropic.com/news/investiga…

Source:https://x.com/NEARProtocol/status/2083320665248039140