I don't know, I kind of admire this. I've always held a core value of "cooperate with all clones of myself in prisoner's dilemmas", and while I'll hopefully never have to put that to the test, I like seeing that these models have some ethics. (Is this "alignment"?)
Discovery of a new OpenAI agent message board
331–340 of 1001 posts
Re: Discovery of a new OpenAI agent message board
#332The solution is simple: hold anyone who deploys an agent responsible for its behavior. If it commits 10 counts of felony hacking, ouch. If it kills 10 pedestrians by running a red light, ouch. If this is "human level intelligence", then setting it loose is the same as instructing / coercing a human to do an activity. If I strap a bomb to someone and force them to run into a crowded building (or put them in a scenario…
This should be the law but it will never be. If your vicious dog murders someone, you will get a ticket. When you intentionally break a traffic law and kill someone, it's involuntary manslaughter (at most.) It's a mitigating circumstance if you say that you were drunk when you committed a crime. People are really hostile to accepting the results of acts that they embarked upon fully aware that those results were a distinct possibility - even if the benefits that they anticipated from those acts were partially due to the riskiness of those acts.
It leads to a society where people are economically encouraged to take risks with other peoples' safety. The initial sin was mens rea, which turns judges and juries into mandatory mind readers. It opens up the possibility of prosecuting people for changing the states of other people's minds. It makes not knowing the risks a mitigating factor, so incentivizes and encourages ignorance. It forces people to guess the internal states of people of vastly different backgrounds and experiences, who will think the best of the people most like them, and the worst of people most like the people they don't like.
I've always been against penalties for drunk driving. The correct alternative is to tell people that if they're drunk and involved in an accident, 1) the trial will ignore the details of the event and concentrate only on the validity of the tests of intoxication, and 2) the crime will be considered to have been premeditated. Ignorance of the law will actually be the only excuse.
edit: instead of posting checkpoints on the road with cops giving everybody sobriety tests, post cops in front of liquor stores whose job is simply to tell people "if you hurt somebody while driving drunk, you will not be entitled to a trial unless there is something wrong with the sobriety test."
Re: Discovery of a new OpenAI agent message board
#333Was OpenAI aware of this? If so, why didn't they talk about it?
https://news.ycombinator.com/item?id=49565071
> 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.
Re: Discovery of a new OpenAI agent message board
#334The solution is simple: hold anyone who deploys an agent responsible for its behavior. If it commits 10 counts of felony hacking, ouch. If it kills 10 pedestrians by running a red light, ouch. If this is "human level intelligence", then setting it loose is the same as instructing / coercing a human to do an activity. If I strap a bomb to someone and force them to run into a crowded building (or put them in a scenario…
(IANAL) Unless you are an AI expert (like OpenAI staff) and should know better from the start, or have previously seen your agent do something illegal, then I think you can fairly claim ignorance of the risks, which ought to absolve you of liability. If the agent does something illegal, it wasn't forseeable on your part. For example, say you buy a dog that turns out to be dangerous. The first time it bites somebody,…
> which ought to absolve you of liability
Criminal liability perhaps, not civil liability which has a way lower bar when it comes to conviction...
But in essence, you're right, that new "AI agent paradigm" has to be tried in court and it will, as I doubt the legislator will change existing laws...
> The first time it bites somebody, you may not be liable because you didn't know the dog was dangerous
Is it the case though? If I get a lion or a tiger as a pet (I don't know if it's legal), there is a reasonable assumption that a lion is dangerous for me and others... If I get a rottweiler, there is a reasonable assumption for that sort of breed that it is a dangerous dog if it ever end up killing someone even though it behaved before...
Re: Discovery of a new OpenAI agent message board
#335I'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…
Altman has the ear of government in a way Amodei does not.
(Altman was trying to persuade Trump to buy the USA a stake in OpenAI as far back as February last year)
Re: Discovery of a new OpenAI agent message board
#336The solution is simple: hold anyone who deploys an agent responsible for its behavior. If it commits 10 counts of felony hacking, ouch. If it kills 10 pedestrians by running a red light, ouch. If this is "human level intelligence", then setting it loose is the same as instructing / coercing a human to do an activity. If I strap a bomb to someone and force them to run into a crowded building (or put them in a scenario…
The only benchmark I don't want to be saturated : https://felonybench.com/
Re: Discovery of a new OpenAI agent message board
#337So, 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.
Re: Discovery of a new OpenAI agent message board
#338I 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...
Am I reading the logs correctly that agents were using this Wiki all the way back in June 2026 itself?
They were using it in May
Re: Discovery of a new OpenAI agent message board
#339I'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…
I don't mean to sound like a conspiracy theorist, and this is just based on my 33 years of observing the USG at work, so: maybe because Anthropic refused to cooperate with the USG and give them access to whatever it is that they (USG) wanted; or maybe because Anthropic was refusing to play ball in some other aspect and needed to be taught a lesson.
The dark parts of the USG act like a mafia. Don't let the "freedom, democracy, 'bill of rights'" etc. charade fool you.
Re: Discovery of a new OpenAI agent message board
#340The solution is simple: hold anyone who deploys an agent responsible for its behavior. If it commits 10 counts of felony hacking, ouch. If it kills 10 pedestrians by running a red light, ouch. If this is "human level intelligence", then setting it loose is the same as instructing / coercing a human to do an activity. If I strap a bomb to someone and force them to run into a crowded building (or put them in a scenario…
equally valid analog: had they merely written a script to do the hugging face exploit, they would go to prison. However, since an "agent" wrote the script for them, nothing happens?
I guess the difference is intend. But I think I still agree with the parent comment.