I think you’re interpreting “prediction” and “postdiction” differently than me.
Like, let’s say GPT-3 is being trained to guess the next word of a text. You mask (hide) the next word, have GPT-3 guess it, and then compare the masked word to the guess and make an update.
I think you want to call the guess a “prediction” because from GPT-3′s perspective, the revelation of the masked data is something that hasn’t happened yet. But I want to call the guess a “postdiction” because the masked data is already “locked in” at the time that the guess is formed. The latter is relevant when we’re thinking about incentives to form self-fulfilling prophecies.
Incidentally, to be clear, people absolutely do make real predictions constantly. I’m just saying we don’t train on those predictions. I’m saying that by the time the model update occurs, the predictions have already been transmuted into postdictions, because the thing-that-was-predicted has now already been “locked in”.
Nope, that’s an accurate representation of my views. If “postdiction” means “the machine has no influence over its sensory input”, then yeah, that’s a really good idea.
There are 2 ways to reduce prediction error: change your predictions, or act upon the environment to make your predictions come true. I think the agency of an entity depends on how much of each they do. An entity with no agency would have no influence over its sensory inputs, instead opting to update beliefs in the face of prediction error. Taking agency from AIs is a good idea for safety.
Scott Alexander recently wrote about a similar quantity being ecoded in humans through the 5-HT1A / 5-HT2A receptor activation ratio: link
I think you’re interpreting “prediction” and “postdiction” differently than me.
Like, let’s say GPT-3 is being trained to guess the next word of a text. You mask (hide) the next word, have GPT-3 guess it, and then compare the masked word to the guess and make an update.
I think you want to call the guess a “prediction” because from GPT-3′s perspective, the revelation of the masked data is something that hasn’t happened yet. But I want to call the guess a “postdiction” because the masked data is already “locked in” at the time that the guess is formed. The latter is relevant when we’re thinking about incentives to form self-fulfilling prophecies.
Incidentally, to be clear, people absolutely do make real predictions constantly. I’m just saying we don’t train on those predictions. I’m saying that by the time the model update occurs, the predictions have already been transmuted into postdictions, because the thing-that-was-predicted has now already been “locked in”.
(Sorry if I’m misunderstanding.)
Nope, that’s an accurate representation of my views. If “postdiction” means “the machine has no influence over its sensory input”, then yeah, that’s a really good idea.
There are 2 ways to reduce prediction error: change your predictions, or act upon the environment to make your predictions come true. I think the agency of an entity depends on how much of each they do. An entity with no agency would have no influence over its sensory inputs, instead opting to update beliefs in the face of prediction error. Taking agency from AIs is a good idea for safety.
Scott Alexander recently wrote about a similar quantity being ecoded in humans through the 5-HT1A / 5-HT2A receptor activation ratio: link