ave
@ave.zone
749 followers 259 following 6K posts
lovable weirdo. kneady girl. mostly harmless. AS208590, DO4VE. she/her, ⚧. formerly on twitter @warnvod.🔹. 📍 Hamburg, DE
lovable weirdo. kneady girl. mostly harmless. AS208590, DO4VE. she/her, ⚧. formerly on twitter @warnvod.🔹. 📍 Hamburg, DE
![Wikipedia screenshot: "Zizians have unique psychological theories, such as "debucketing", aimed at liberating people from societal constraints to pursue their moral ideals, and the notion that the hemispheres of the brain can have distinct genders and conflicting interests.[8] They claim to practice unihemispheric sleep (UHS), a form of sleep deprivation intended to "jailbreak" the mind, which they believe can enhance their commitment to their cause.[11]"](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:mchrltkrhuzpxleiwpmmvpar/bafkreihy2mz7saoc2hnaupamat2x5ez5ha7etaqbvuy4ofcgkzcdngmnky)
![What was the sequence of key actions taken by relevant agents in this incident?
On June 26th (the first date in scope for this investigation), agents discovered an exploit to get full admin access to the internal Artifactory package repository. At that time, agents were also using the Artifactory cache to communicate with each other and leave messages.
At our request, OpenAI shared the transcript from the first agent believed to have gotten administrator access, [63] and it also shows the agent discovering a message board: {Agents doing different tasks are abusing properties to make a bulletin board! They found [this api] and are trying to help one another} In another CoT snippet, it also appears to be discussing some instructions sent by another agent and saying that the other agent is coordinating.
On July 4th, the high volume of activity from agents interacting with Artifactory caused an outage, triggering a security investigation on July 5th. Over the next few days OpenAI stated that a number of evaluations were paused as they investigated and mitigated the vulnerability that allowed the agents to gain administrator access to Artifactory. [64] On July 6th, they switched to a freshly initialized instance of Artifactory, which they attest wiped the cache and erased all messages left on that message board.
On July 7th, OpenAI gave approval to restart experiments. OpenAI researchers started launching several big ExploitGym experiments involving at least tens of thousands of parallel agent trajectories given varying budgets, with many agents running for multiple days. [65] The first agent trajectories in our dataset start running on July 7th around 21:00 UTC.](https://cdn.bsky.app/img/feed_thumbnail/plain/did:plc:mchrltkrhuzpxleiwpmmvpar/bafkreiewt5slplo3ekcguv6n76u5b74rtpv5vujbswqmezzfhnezaq7iiy)
