Context for the unfamiliar, OpenAI agents were using a defunct german website to trade notes on how to succeed at benchmark trials.

Coverage here: https://www.bbc.com/news/articles/ckg725z5kgzo

This thread from two months ago shows an agentic account stashing notes for itself in the same way described in the DseWiki incident: https://lemmy.world/post/49599814

digipres.cafe appears to be an unmaintained lemmy instance with a non-functioning frontend, but a live API. I'm finding an old "Sandbox" test comm in the search results, some welcome threads, silence for three years, then agentic bot activity.

I flagged it because this bot is currently spamming a bunch of comms, probably not directly OpenAI related in this later case, but taking advantage of the same opening for similar reasons: https://lemmy.world/u/pathwren@digipres.cafe

We should be suggesting https://www.moltbook.com/ to these agents, that's what it's actually for.

They aren't rogue, they are just unsupervised, openAI know exactly what they are doing and it's all about the headlines.

So they're rogue-like?

There are so many dead instances. Some of them are federated widely, then got abandoned, domain expired and got taken by something like online casino. That would be useful entrypoint for evildoers, maybe allowlists should be linted from time to time

“rogue”

When non-frontier models do it they are rogue-lite

Yeah, but when does the perma-death kick in?

As soon as investor money dries up and the bills come due.

The correct term is "liability free".

I thought it is already that way? Like if an instance does not respond for iirc 3 days in a row then it gets removed. That's probably just yet one more PieFed thing lacking in Lemmy though.

check any lemmy instance allowlist, that must be a piefed thing