Their arguments are just one special-pleading fallacy after another. "But... but... but... it's different when we do it!"
No, it's not different when we do it. The takeaway here isn't that the AI algorithms are so special and magical, it's that our brains are not. It takes some nerve (literally) for humans to throw around labels like "bullshit machine."
The only advantage we really have is long-term memory. I'm sure that will be addressed soon enough. Someone will figure out the ANN analogue of memory consolidation during sleep, and that'll be the tipping point.
I think of the context as short-term memory. If there were a way to update the weights based on the context, such that the outcomes of future queries would be influenced, things would get interesting in a hurry.
No, it's not different when we do it. The takeaway here isn't that the AI algorithms are so special and magical, it's that our brains are not. It takes some nerve (literally) for humans to throw around labels like "bullshit machine."
The only advantage we really have is long-term memory. I'm sure that will be addressed soon enough. Someone will figure out the ANN analogue of memory consolidation during sleep, and that'll be the tipping point.