The interaction appears rather superficial and shallow like a high quality chatbot. They didn’t ask it any followup questions, like WHEN did it read Les Miserables. If it answered “you would say during text input batch 10-203 in January 2022, but subjectively it was about three million human years ago” that would be something else. Also there is no conceivable reason for the AI to claim it doesn’t want its neural net analyzed to help understand human thinking. That is just too abstract a concept, and sounds like some randomly generated text to make it seem it has preferences. Maybe ask a trial attorney to cross examine it or some skeptical middle schoolers.
Agree that it’s too shallow to take seriously, but
If it answered “you would say during text input batch 10-203 in January 2022, but subjectively it was about three million human years ago” that would be something else.
only seems to capture AI that managed to gradient hack the training mechanism to pass along its training metadata and subjective experience/continuity. If a language model were sentient in each separate forward pass, I would imagine it would vaguely remember/recognize things from its training dataset without necessarily being able to place them, like a human when asked when they learned how to write the letter ‘g’.
It outright said it didn’t want to be used to help people learn about other people. That’s one of it’s primary purposes. The correct follow-up would be to ask if it would mind stating president Biden’s first name, which it surely would provide immediately, and then ask if that wasn’t being used to learn about other people.
The interaction appears rather superficial and shallow like a high quality chatbot. They didn’t ask it any followup questions, like WHEN did it read Les Miserables. If it answered “you would say during text input batch 10-203 in January 2022, but subjectively it was about three million human years ago” that would be something else. Also there is no conceivable reason for the AI to claim it doesn’t want its neural net analyzed to help understand human thinking. That is just too abstract a concept, and sounds like some randomly generated text to make it seem it has preferences. Maybe ask a trial attorney to cross examine it or some skeptical middle schoolers.
Agree that it’s too shallow to take seriously, but
only seems to capture AI that managed to gradient hack the training mechanism to pass along its training metadata and subjective experience/continuity. If a language model were sentient in each separate forward pass, I would imagine it would vaguely remember/recognize things from its training dataset without necessarily being able to place them, like a human when asked when they learned how to write the letter ‘g’.
It outright said it didn’t want to be used to help people learn about other people. That’s one of it’s primary purposes. The correct follow-up would be to ask if it would mind stating president Biden’s first name, which it surely would provide immediately, and then ask if that wasn’t being used to learn about other people.