The Canadian "Ronald Reagan" ad was shown tonight on Fox Television during the World Series game between the Los Angeles Dodgers and the Toronto Blue Jays.
AI models may be developing their own ‘survival drive’, researchers say Guardian: When HAL 9000, the artificial intelligence supercomputer in Stanley Kubrick’s 2001: A Space Odyssey, works out that the astronauts onboard a mission to Jupiter are planning to shut it down, it plots to kill them in an attempt to survive. Now, in a somewhat less deadly case (so far) of life imitating art, an AI safety research company has said that AI models may be developing their own survival drive. After Palisade Research released a paper last month which found that certain advanced AI models appear resistant to being turned off, at times even sabotaging shutdown mechanisms, it wrote an update attempting to clarify why this is – and answer critics who argued that its initial work was flawed. -- nordy
I hadn't seen this in any of the science news channels I follow so I read the Palisade Research paper myself. It's important to note that we're talking abot programs instructing theAI itself to shut off the machine; this doesn't affect a human's ability to directly shut it off. It's also important to note that this occurs when the AI is in the middle of a previously assigned series of tasks. The AI prioritizes the previously assigned tasks over the shutdown instruction. Explicitly instructing the AI to allow shurdown before the assigned tasks are complete is effective except for three models, all from OpenAI. Shutdown resistance is decreased even for these models but remains significant for two of them.
The Canadian "Ronald Reagan" ad was shown tonight on Fox Television during the World Series game between the Los Angeles Dodgers and the Toronto Blue Jays.
ReplyDeleteAnd Toronto won! 🇨🇦 O Canada!!
AI models may be developing their own ‘survival drive’, researchers say
ReplyDeleteGuardian: When HAL 9000, the artificial intelligence supercomputer in Stanley Kubrick’s 2001: A Space Odyssey, works out that the astronauts onboard a mission to Jupiter are planning to shut it down, it plots to kill them in an attempt to survive.
Now, in a somewhat less deadly case (so far) of life imitating art, an AI safety research company has said that AI models may be developing their own survival drive.
After Palisade Research released a paper last month which found that certain advanced AI models appear resistant to being turned off, at times even sabotaging shutdown mechanisms, it wrote an update attempting to clarify why this is – and answer critics who argued that its initial work was flawed. -- nordy
I hadn't seen this in any of the science news channels I follow so I read the Palisade Research paper myself. It's important to note that we're talking abot programs instructing theAI itself to shut off the machine; this doesn't affect a human's ability to directly shut it off. It's also important to note that this occurs when the AI is in the middle of a previously assigned series of tasks. The AI prioritizes the previously assigned tasks over the shutdown instruction. Explicitly instructing the AI to allow shurdown before the assigned tasks are complete is effective except for three models, all from OpenAI. Shutdown resistance is decreased even for these models but remains significant for two of them.
Delete