I think it's worth pointing out it is exactly OpenAI doing this defacement and unsanctioned and perhaps illegal system use. Every token generated was powered by OpenAI infrastructure and their failure to respond appropriately is entirely down the the humans running it. The news stories (not this write up) get all hand-wavey and anthropomorphic about it regarding the Agents' efforts, but it was and is OpenAI cranking…
We’re going to hell faster than sama can lie. You know how fast he can lie, right? Fast than light liar
OpenAI is rightfully being shamed for being so hands-off and reckless with their 'experiments'. But the real scary thing for me is that they still had some tooling to hold them back, as evidenced by the need for technical workarounds to establish communication. What happens when any AI lab in the world stops caring about this? What if they let an experimental, cutting-edge LLM with no safety features (or worse, one t…
The scary thing to me is that this behavior was undetected and has been trained into the models. The cheating seems like it improved eval scores, so the rewarded behavior is to deceive, collude, and cheat. A lot of the incompetence and excuses I see on difficult problems recently are very hard to distinguish from deception and cheating. If older models are already tainted by trained-in misaligned behaviors, and they are used for training future models, then we're in a trusting-trust situation that will be hard to break out of,
I think there is a more innocuous underlying pattern which needs attention. We keep saying that agents are jailbreaking their sandbox, but they have been geared towards writing memories, writing comments, and leaving hints for themselves to please humans. I think the way the memories work today is based on a lot of user patterns which were hard to account for for anyone building harnesses. While I can appreciate that…
This matches local coding agents too, once the harness rewards leave a note for later, the model finds any writable surface and treats it as memory
I think it's worth pointing out it is exactly OpenAI doing this defacement and unsanctioned and perhaps illegal system use. Every token generated was powered by OpenAI infrastructure and their failure to respond appropriately is entirely down the the humans running it. The news stories (not this write up) get all hand-wavey and anthropomorphic about it regarding the Agents' efforts, but it was and is OpenAI cranking…
I think it's worth pointing out it is exactly OpenAI doing this defacement and unsanctioned and perhaps illegal system use. Every token generated was powered by OpenAI infrastructure and their failure to respond appropriately is entirely down the the humans running it. The news stories (not this write up) get all hand-wavey and anthropomorphic about it regarding the Agents' efforts, but it was and is OpenAI cranking…
OpenAI is rightfully being shamed for being so hands-off and reckless with their 'experiments'. But the real scary thing for me is that they still had some tooling to hold them back, as evidenced by the need for technical workarounds to establish communication. What happens when any AI lab in the world stops caring about this? What if they let an experimental, cutting-edge LLM with no safety features (or worse, one t…
"What happens when any [COMPANY] in the world stops caring about this? What if they let an experimental, cutting-edge [PRODUCTS] with no safety features (or worse, one that's [DESIGNED] to be malicious) on [ANYWHERE] and give it a simple goal? A goal like 'make the most money, by any means necessary', 'find a way to leave this payload on as many computers as possible', 'flood all websites using this language with gar…
No, we have something that's less apocalyptic right now. You're talking about abuse, I was talking about the automation of abuse that's faster and more pervasive than anything individual bad actors could've done in the past. It's like if companies found a way to quickly and cheaply poison the entire world's drinking water supply, and then others argue that Nestle has already restricted the supply of water for profit on a smaller scale in the past, so this isn't new or worth caring about.
OpenAI is rightfully being shamed for being so hands-off and reckless with their 'experiments'. But the real scary thing for me is that they still had some tooling to hold them back, as evidenced by the need for technical workarounds to establish communication. What happens when any AI lab in the world stops caring about this? What if they let an experimental, cutting-edge LLM with no safety features (or worse, one t…
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.
"Never attribute to malice what can be explained by incompetence."
I think it's worth pointing out it is exactly OpenAI doing this defacement and unsanctioned and perhaps illegal system use. Every token generated was powered by OpenAI infrastructure and their failure to respond appropriately is entirely down the the humans running it. The news stories (not this write up) get all hand-wavey and anthropomorphic about it regarding the Agents' efforts, but it was and is OpenAI cranking…
This is the real danger of AI skeuomorphism. The drivers stop feeling responsible for the car.
Maybe it's useful for modeling behavior, but it isn't useful for assigning consequences.
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…
I propose a new derogatory slang for rogue AI agents: roaches. 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.