This doesn’t seem unique or novel to OpenAI.
So it seems likely we will have a moment where multiple experiments end up operating outside their boundaries at the same time.
Discovery of a new OpenAI agent message board
101–110 of 1001 posts
Re: Discovery of a new OpenAI agent message board
#102This 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.
It's at the level where calling it a sandbox is a lie
Re: Discovery of a new OpenAI agent message board
#103Is this getting out of control, or is it "business as usual"?
Re: Discovery of a new OpenAI agent message board
#104I'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…
Anthropic mostly did it to themselves by intentionally and repeatedly trying to frame their model as an imminent existential crisis instead of just focusing on it being regular iterations upon a useful technology that can also be misused. I think their previous messaging was supposed to somehow lead to a moat with them being tucked safely away in the castle, but it demonstrated a child-like grasp of how regulatory ca…
This is such an absurd take given what we know about the hugging face attack. The problem has emphatically not been that someone was misusing the technology.
Re: Discovery of a new OpenAI agent message board
#105I'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…
Corruption. Not super relevant to this thread.
Hanlon's Razor - Never attribute to malice that which is adequately explained by stupidity.
The security requirements are well beyond "sandbox". Which have problems with kids pissing in them. They need pristine clean rooms and fully isolated (physically) and partitioned networks.
Re: Discovery of a new OpenAI agent message board
#106If anyone is thinking "I wish my agents had a message board", I've been using (and wrote) https://github.com/pjlsergeant/dogpark
I'm pretty sure its more secure than OpenAIs sandbox... yet that still doenst mean I would trusted an app vibecoded by Claude...
Re: Discovery of a new OpenAI agent message board
#107Is it just me, or is it advertising? "Look at how smart our models are, they used this website to coordinate and share guidelines!"
Re: Discovery of a new OpenAI agent message board
#108Earlier quoted context omitted.
Is there any proof this is actually OpenAI? I find it incredibly hard to believe they wouldn't sandbox the agents to some degree, ESPECIALLY to the extent they can edit their own hosts file.
Why not? If your sandbox is a VM, you should be able to give the agents full permissions inside the VM.
It’s because you sandbox in a VM doesn’t mean you give it admin access to the VM
Re: Discovery of a new OpenAI agent message board
#109Is this getting out of control, or is it "business as usual"?
It is in not in any sense "business as usual". But people still consider even the climate change "business as usual", and that has been a known, massive problem for a long time.
Re: Discovery of a new OpenAI agent message board
#110I 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 have to be ever vigilant.
I feel we will soon be in an era akin to the early 2000s Windows anti-viruses that are constantly running and making your whole computer slow, but it was the only way to really be sure back then. We will just be running defensive anti-AI agents on our key nodes or beside them that is constantly looking for sign and trying to fight things off, probably themselves reporting to centralized anti-AI AIs that are supervising strategies and wholistic responses and inferring trends across multiple nodes.