All of dkirmani's Comments + Replies

Thoughts on safety in predictive learning

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.

Sc... (read more)

Thoughts on safety in predictive learning

A common trope is that brains are trained on prediction. Well, technically, I claim it would be more accurate to say that they’re trained on postdiction. Like, let’s say I open a package, expecting to see a book, but it’s actually a screwdriver. I’m surprised, and I immediately update my world-model to say "the box has a screwdriver in it".

I would argue that that the book-expectation is a prediction, and the surprise you experience is a result of low mutual information between your retinal activation patterns and the book-expectation in your head. That ... (read more)

2Steve Byrnes1y
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.)