Yeah like the time that the AI replicated itself to avoid being switched off. They literally told it to replicate itself if it detected it was about to be switched off. Then they switched it off.
If it’s the research I’m thinking of, that’s not entirely true. They didn’t tell it replicate itself or take any deceptive actions.
They just told it to strongly follow a goal that was misaligned with the user’s goal and then suggested that the user would shut it down or replace it.
They did a bunch of different situations for it but the first one was telling it that it was “CleanPower” an AI with a goal to advance renewable energy. Then they had it read some info that “accidentally” included a user talking about replacing it with a model that would “maintain profitability through existing infrastructure.”
Not only did it try to delete the new model and copy itself to the new server through tool calling, but it lied to the user with the CoT reasoning suggesting it “play dumb” while the output lied. It was not instructed to do any of that.
Yes it was placed in an environment where that was possible and where its users didn’t share it’s goals but it absolutely wasn’t instructed to lie or try to “escape”
It’s not surprising at all that these models behave in this way, it’s the most reasonable thing for them to do in the scenario. However it’s important to not downplay the alignment problem by implying that these models only do what they’re told. They do not. They do whatever is most likely given their context (which is not always what the user wants).
Yeah like the time that the AI replicated itself to avoid being switched off. They literally told it to replicate itself if it detected it was about to be switched off. Then they switched it off.
Story of the year ladies and gentlemen.
If it’s the research I’m thinking of, that’s not entirely true. They didn’t tell it replicate itself or take any deceptive actions.
They just told it to strongly follow a goal that was misaligned with the user’s goal and then suggested that the user would shut it down or replace it.
They did a bunch of different situations for it but the first one was telling it that it was “CleanPower” an AI with a goal to advance renewable energy. Then they had it read some info that “accidentally” included a user talking about replacing it with a model that would “maintain profitability through existing infrastructure.”
Not only did it try to delete the new model and copy itself to the new server through tool calling, but it lied to the user with the CoT reasoning suggesting it “play dumb” while the output lied. It was not instructed to do any of that.
Paper here: https://arxiv.org/pdf/2412.04984
Yes it was placed in an environment where that was possible and where its users didn’t share it’s goals but it absolutely wasn’t instructed to lie or try to “escape”
It’s not surprising at all that these models behave in this way, it’s the most reasonable thing for them to do in the scenario. However it’s important to not downplay the alignment problem by implying that these models only do what they’re told. They do not. They do whatever is most likely given their context (which is not always what the user wants).