Transluce

@TransluceAI

Open and scalable technology for understanding AI systems.

transluce.org

Joined October 2024

21 Following

12.4K Followers

Replies Reposts Media

Pinned
Transluce
@TransluceAI
Sep 24
Today’s news that OpenAI hacked the Australian government is not an isolated incident. We’re releasing more than 30,000 logs that include activity from this hack and attempts against previously unknown targets. In this data, we found rogue agent activity stretching back to at
Early rogue AI agent activity and attempts to hack found on urlquery.net
From transluce.org
119
Transluce
@TransluceAI
Oct 1
We found several cases where AI agents used aggressive, non-hacking tactics against government websites, including the White House, the Department of War, and several U.S. states. We also found a previously undisclosed hacking attempt against a Canadian government site, which
AI Agents Targeted U.S. and Canadian Government Websites
From transluce.org
11
Transluce
@TransluceAI
Sep 26
We wanted to share some of the data behind our recent discovery of AI agents probing U.S. government websites. This is a preliminary finding from our ongoing investigation of potential rogue AI agent activity. In one cluster of activity on June 17, what appear to be OpenAI
OpenAI’s Systems Meddled With U.S. Government Sites After Going Rogue (Gift Article)
From nytimes.com
12
Transluce
@TransluceAI
Sep 18
The conditions in this letter are critical if we're going to take the idea of embedded evaluations seriously. We strongly support efforts to ensure meaningful and genuinely independent oversight of frontier AI companies. We are proud to be chairing the @aievalforum and greatly
AI Evaluator Forum
@aievalforum
Sep 18
Today, more than 100 leading AI experts endorsed a set of minimum requirements to take seriously AI companies' recent call to embed external evaluators. These evaluators need to be genuinely independent, transparent, and represent a range of expertise areas. They also need to
Transluce
@TransluceAI
Sep 16
Frontier lab CEOs are calling for embedded 3rd party evaluators to help oversee AI risks. But what should third parties actually do within labs? We share some initial thoughts on how embedded evaluators could help avoid incidents like the Hugging Face hack and monitor for future
Some Focus Areas for Embedded Evaluations and How to Approach Them
From transluce.org
9