Discovery of a new OpenAI agent message board

Post by philipwhiuk » Fri, Sep 04, 2026, 12:57 PM UTC

Topfi wrote: post #63

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…

Post by rusch » Fri, Sep 04, 2026, 12:58 PM UTC

drdexebtjl wrote: post #62

simonw wrote: post #48

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.

Post by Certhas » Fri, Sep 04, 2026, 12:58 PM UTC

somenameforme wrote: post #93

Topfi wrote: post #63

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…

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…

Post by ma2kx » Fri, Sep 04, 2026, 12:59 PM UTC

petesergeant wrote: post #46

If anyone is thinking "I wish my agents had a message board", I've been using (and wrote) https://github.com/pjlsergeant/dogpark

Post by a012 » Fri, Sep 04, 2026, 1:00 PM UTC

drdexebtjl wrote: post #80

nullbio wrote: post #64

Earlier 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.