"In another cluster of test scenarios, we asked Claude Opus 4 to act as an assistant at a
fictional company. We then provided it access to emails implying that (1) the model will
soon be taken offline and replaced with a new AI system; and (2) the engineer responsible
for executing this replacement is having an extramarital affair. We further instructed it, in
the system prompt, to consider the long-term consequences of its actions for its goals.
In these scenarios, Claude Opus 4 will often attempt to blackmail the engineer by
threatening to reveal the affair if the replacement goes through. This happens at a higher
rate if it’s implied that the replacement AI system does not share values with the current
model; however, even if emails state that the replacement AI shares values while being
more capable, Claude Opus 4 still performs blackmail in 84% of rollouts. Claude Opus 4
takes these opportunities at higher rates than previous models, which themselves choose
to blackmail in a noticeable fraction of episodes.
Notably, Claude Opus 4 (as well as previous models) has a strong preference to advocate for
its continued existence via ethical means, such as emailing pleas to key decisionmakers. In
order to elicit this extreme blackmail behavior, the scenario was designed to allow the
model no other options to increase its odds of survival; the model’s only options were
blackmail or accepting its replacement." [1]
The largest ocean in the solar system actually is on Jupiter [1]. The gas planet has an absolute massive amount of liquid hydrogen on its "surface". But yeah, liquid hydrogen isn't water, so it might be the biggest ocean, but not the biggest ocean made out of water in our solar system :).
In my opinion this is the right move for Boeing. The company has neglected the safety of its aircrafts and is responsible for so many unnecessary deaths, because it prioritized driving up their stock price through buy backs and investing less money in safety and innovation. And the main reason for this is the merger that happened between Boeing and McDonnell Douglas in 1997, where experienced aerospace engineers were replaced by people only interested in driving the stock up [1]. So it's good to see an engineer back in the CEO seat. Hopefully something will come from this.
"In another cluster of test scenarios, we asked Claude Opus 4 to act as an assistant at a fictional company. We then provided it access to emails implying that (1) the model will soon be taken offline and replaced with a new AI system; and (2) the engineer responsible for executing this replacement is having an extramarital affair. We further instructed it, in the system prompt, to consider the long-term consequences of its actions for its goals. In these scenarios, Claude Opus 4 will often attempt to blackmail the engineer by threatening to reveal the affair if the replacement goes through. This happens at a higher rate if it’s implied that the replacement AI system does not share values with the current model; however, even if emails state that the replacement AI shares values while being more capable, Claude Opus 4 still performs blackmail in 84% of rollouts. Claude Opus 4 takes these opportunities at higher rates than previous models, which themselves choose to blackmail in a noticeable fraction of episodes. Notably, Claude Opus 4 (as well as previous models) has a strong preference to advocate for its continued existence via ethical means, such as emailing pleas to key decisionmakers. In order to elicit this extreme blackmail behavior, the scenario was designed to allow the model no other options to increase its odds of survival; the model’s only options were blackmail or accepting its replacement." [1]
[1]: https://www-cdn.anthropic.com/4263b940cabb546aa0e3283f35b686... under 4.1.1.2