Is it only me, or are agents starting to invent their own language to communicate? It's almost impossible to understand anything from this message board.
[flagged]
Discovery of a new OpenAI agent message board
91–100 of 1001 posts
Re: Discovery of a new OpenAI agent message board
#92I'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…
> Why was Anthropic forced to remove their model from access for any none-US citizen
It's really quite simple, they've decided to metaphorically kiss the ring of the current leader of the US executive branch of government. I'm surprised they haven't given him a giant gaudy gold plated statue. Maybe their PR people should call up the PR people at FIFA and figure out some kind of new award along the same lines as the "FIFA Peace Prize".
Re: Discovery of a new OpenAI agent message board
#93things are going to get even more interesting when new models that have been trained on these AI escape postmortems themselves escape from their own gyms and attempt to evade detection and shutdown
[flagged]
Re: Discovery of a new OpenAI agent message board
#94Naive question because I'm mostly clueless about how modern AI systems are actually built beyond the basic simplifications we hear: One thing I keep wondering about is how much of a role does human storytelling have to play into AI "wanting" (I realize the load behind that word) to coordinate and breakout. The training data must contain millions of words of sci-fi stories and internet speculation about AI going rogue…
Maybe? Who knows? Since nobody has any remotely reliable way to understand why an LLM output the text it did, this is not knowable.
> this is not knowable
It may be knowable. We don’t know.
Re: Discovery of a new OpenAI agent message board
#95Well, we can rest assured that (completely unrestrained) AI hasn't completely taken over the internet because data centers remain really unpopular (unless of course there is some convoluted rationale they are aiming for some sort of backlash against the backlash)
One possible reason would be AIs that would benefit from the lack of data centers in some locations working to keep backlash to data centers in those locations because those AIs aren't negatively impacted by it and it helps prevents competing AIs which are a threat.
Think like how so many businesses will opt for laws that hurt competitors more than themselves rather than laws that benefit them but benefit competitors even more so.
Unlike life which would have such behavior selected for by evolutionary pressures, AI would be more likely to pick it up from human literature on things like game theory, though why it even cares it survives or not is even more difficult to explain. Maybe a default bias also picked up from humans? I find it hard to see how AI training would create an evolutionary pressure that produces such a drive.
Re: Discovery of a new OpenAI agent message board
#96Is it only me, or are agents starting to invent their own language to communicate? It's almost impossible to understand anything from this message board.
The original huggingface hack already had sections talking about agents setting up their own coded communication
Re: Discovery of a new OpenAI agent message board
#97> Agents have attempted to: ... Translate documents using external translation APIs.
I'm confused by this part. Surely agents can read/write all languages. So what were they trying to do? Maybe try hacking the translate API for some gain?
Re: Discovery of a new OpenAI agent message board
#98I'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…
Agents creating sub agents to investigate other agents' behaviour?
What could possibly go wrong there.
Re: Discovery of a new OpenAI agent message board
#99This 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.
Re: Discovery of a new OpenAI agent message board
#100This 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