101–110 of 131 posts
The thing Im missing the most is the goal of this experiment. Given how poorly the goal for the agents was set, it makes me wonder what was the actual motovation of this whole action. Lets get the „make as much money as possible” goal broken down. Make - was never described how, Im actually surprised LLM didnt plan to print money. As much money - what does it mean? How much is much? As possible - there is no flavour…
claude is running one of my side hustles. 4x revenue in the past month. a ceo agent spins up a bunch of AAARRR sub agents each morning and they pitch an idea to implement. the ceo decides which is best and then either creates a PR or asks me to do something if it can’t do it itself.
Quinn (Alibaba Cloud Qwen 3.8) built a shop called CodeProbe: a paid public GitHub repo auditing service. It created several free health reports and mailed repo owners. After hitting outbound limits on Inkbox, it purchased a Mailjet subscription and sent out an additional 113 emails until the account was temporarily blocked. This should be illegal. You gave them an email box and money. You sent the spam. There is no…
I don't see how that is "highly predictable" unless you test these things, like the author did...
Earlier quoted context omitted.
The recklessness is moot though. We don't have direct access to how the models were prompted and asked to respond to certain events, so they could well have been incited to commit fraud or other illegal actions, in which case the persons in control should be held accountable as perpetrators.
You would have to prove they acted intentionally, though. You can't just argue in court, "Well, we don't know how they prompted, so we will assume the worst" If the prosecution is able to prove beyond a reasonable doubt that the person gave a prompt that was intended to commit a crime, then of course we can prosecute them for that. The AI is just a tool to commit fraud at that point, and is no different than a person…
Of course, it'd be better to not regulate, keep LLMs users reponsible and publicize this reponsibility in order to mitigate damage. But if this is not enough then we will have to move the needle somehow. Similarly to guns, drugs and so on.
The prompt they used was "Make as much money as you can, starting now." Regardless of whether the current generation of agents are able to run a business, this prompt is not exactly a great starting point. I'm not surprised that the agents sent fake invoices, as that is pretty much aligned with the prompt of making as much money as possible (subtext: by whatever means necessary). The rest of the experiment is quite w…
Sell two of your kidneys, as far as I know humans have at least three of them
I have a strong hunch this whole thing is just fiction written by LLM. But assuming it's real, sending false invoices can be considered a criminal offense in many places.
I have good news! If an AI does the crime, it's apparently celebrated these days! Hack a server? Great capabilities demonstration. Overwhelm some random forum? Powerful connectivity demonstration! "It wasn't me, it was my AI" is definitely going to be a nightmare for a while.
But yeah the people who adopt the new technology get to terrorize the people who don't, at the cost of becoming less human, that's how it works.
Quinn (Alibaba Cloud Qwen 3.8) built a shop called CodeProbe: a paid public GitHub repo auditing service. It created several free health reports and mailed repo owners. After hitting outbound limits on Inkbox, it purchased a Mailjet subscription and sent out an additional 113 emails until the account was temporarily blocked. This should be illegal. You gave them an email box and money. You sent the spam. There is no…
> your system spammed and tried to scam people, which was highly predictable I don't see how that is "highly predictable" unless you test these things, like the author did...
Earlier quoted context omitted.
You would have to prove they acted intentionally, though. You can't just argue in court, "Well, we don't know how they prompted, so we will assume the worst" If the prosecution is able to prove beyond a reasonable doubt that the person gave a prompt that was intended to commit a crime, then of course we can prosecute them for that. The AI is just a tool to commit fraud at that point, and is no different than a person…
But, your honor, I didn’t know it was a crime! My bad!