Hacker News new | ask | show | jobs
by howscrewedami 1210 days ago
There have been many proposed solutions to the so called "hard problem" of consciousness. We can easily find some with a quick google search. Even its' existence has been debated by multiple scholars / philosophers - wikipedia has a list with some: https://en.wikipedia.org/wiki/Hard_problem_of_consciousness

> There's no way to know if/what an AI experiences

Getting the state of neural net, at a given point in time, is easy. There are many ways to see exactly which neurons activate, why they activate, how much they activate, etc. For smaller neural nets, this is actually easy to do - here's a blog post about it:

https://distill.pub/2020/circuits/visualizing-weights/

As neural nets get larger and larger, interpretability gets harder and harder. However, I wouldn't say it's impossible.

1 comments

It seems you don’t fully understand parent comment and the problem itself. Capturing signals from you eye nerve doesn’t tell anything about your subjective experience of seeing an apple. The only way to understand that you’re seeing an apple from this signal is to train a model on your responses. This is how AI works. It’s a statistical imitation.

The only way for your statement to be true is if you’d be an imitation yourself, not capable of experiencing directly. Which is actually possible, see “pholosophical zombie” concept.

I’m joking of course about you being an imitation. Or do I? :)

> Capturing signals from you eye nerve doesn’t tell anything about your subjective experience of seeing an apple.

I strongly disagree. It actually does tell you quite a lot. For example, if there aren't any signals, you're very likely not seeing anything.

> The only way to understand that you’re seeing an apple from this signal is to train a model on your responses

It seems to me this contradicts your first argument. If such models exist (they very likely do, I'm not familiar with this area of research), they can tell us a lot about a person's experience.

> see “pholosophical zombie” concept.

Searched for “pholosophical zombie” but couldn't find anything, sorry. Just kidding :)