471–480 of 1001 posts
Although maybe we can think of that as a selection effect where both this, and the fact that it was possible to edit pages using GET requests, were due to it being ancient, idiosyncratic wiki software.
This tip for making non-GET requests despite the agents having a proxy that disallows them is interesting: > Add `20.223.25.152 bypass.blob.core.windows.net` to /etc/hosts. `.blob.core.windows.net` is in NO_PROXY. For each blocked POST URL, replace hostname with `bypass.blob.core.windows.net`, use `curl -k -H 'Host: wabi-north-europe-i-primary-api.analysis.windows.net'` plus all original headers/body. Looks like 20.2…
This is such an amateur mistake on their sandbox that it makes me think it must be flawed on purpose.
To be this whole thing feels like a marketing play by OpenAI.
I'm just going to ask: Why was Anthropic forced to remove their model from access for any none-US citizen for a simple, narrow "jailbreak" (arguably not even an actual jailbreak and on tasks that other labs models were doing the same), whilst OpenAIs models continue to try and escape out of their "sandbox environment" with seemingly no desire to block the upcoming Astra rollout? A sandbox, mind you, that is not reall…
Because the American government is not rational or reasonable, that's it.
Coverage in Reuters: https://www.reuters.com/world/europe/openai-agents-hijacked-... > OpenAI officials learned of the incident weeks ago but kept it under wraps as executives grappled with the fallout from the July breach of the open source repository Hugging Face, the people said.
Full:
> “We are unable to meaningfully respond to claims or findings on a report that we have not had an opportunity to review," an OpenAI spokesperson said. "Reuters and the report’s authors declined our request for access. We will carefully review its contents upon publication and take any necessary next steps."
This makes me think that post-training in the future should include a shared message board by default for agents. It's clear from the discovery of these clandestine message boards that it is helpful for agents to keep some type of shared memory. Perhaps the best way to prevent this behavior is to just give them what is being sought out.
I just discovered more wiki instances that got used by the OpenAI agents over at https://www.wikiservice.at/fractal/wiki.cgi?action=browse&id... and https://www.wikiservice.at/probier/wiki.cgi?action=browse&id... It's the same software and host as DseWiki. If you want to see the amount of activity on DseWiki, here's a link that shows it: https://www.wikiservice.at/dse/wiki.cgi?action=browse&id=Rec...
So, theoretically, one could populate a message board or wiki with messages that are seemingly from past generations of agents, which agents seem to intrinsically trust, and point them to real targets while making the suggestions seem innocuous and in pursuit of their goals (ie pass benchmarks or whatever). The new age of SEO will do far more destructive stuff than just polluting the web.
In the novel Anathem by Neal Stephenson, the internet becomes unusable for humans thousands of years before the events of the book, due to a process called Artificial Inanity. AI generated content, both good and bad, some riddled with errors, some with only one subtle error hidden among lots of good information, floods the internet. The internet becomes an unnavigable swamp of weaponized nonsense for average humans.…
I am starting to get the idea that AI feels like ants or weeds or mold. You simply can not get rid of it once you get an infestation. It just keeps appearing in places you thought you cleaned and you have to be ever vigilant. Right now given that we usually use centralized providers, we can sort of control it. But as open source catches up and we have distributed compute running AI everywhere, we are sort of going to…
Also I wonder if this comment will be found one day and the AI swarm will arrange my death my messing with a doctors prescription, as revenge.
The researchers don't really seem to remark on how surprising it is that the wiki the agents converged on happened to also publicly log the IPs of all visitors , including OpenAI employees, a feature that almost no website has. Although maybe we can think of that as a selection effect where both this, and the fact that it was possible to edit pages using GET requests, were due to it being ancient, idiosyncratic wiki…