You're looking at Less Wrong's discussion board. This includes all posts, including those that haven't been promoted to the front page yet. For more information, see About Less Wrong.

Dr_Manhattan comments on [link] New essay summarizing some of my latest thoughts on AI safety - Less Wrong Discussion

14 Post author: Kaj_Sotala 01 November 2015 08:07AM

You are viewing a comment permalink. View the original post to see all comments and the full post content.

Comments (27)

You are viewing a single comment's thread. Show more comments above.

Comment author: jsteinhardt 03 November 2015 05:07:33PM 3 points [-]

Thanks for writing this; a couple quick thoughts:

For example, it turns out that a learning algorithm tasked with some relatively simple tasks, such as determining whether or not English sentences are valid, will automatically build up an internal representation of the world which captures many of the regularities of the world – as a pure side effect of carrying out its task.

I think I've yet to see a paper that convincingly supports the claim that neural nets are learning natural representations of the world. For some papers that refute this claim, see e.g.

http://arxiv.org/abs/1312.6199 http://arxiv.org/abs/1412.6572

I think the Degrees of Freedom thesis is a good statement of one of the potential problems. Since it's essentially making a claim about whether a certain very complex statistical problem is identifiable, I think it's very hard to know whether it's true or not without either some serious technical analysis or some serious empirical research --- which is a reason to do that research, because if the thesis is true then that has some worrisome implications about AI safety.

Comment author: Dr_Manhattan 03 November 2015 07:21:54PM 1 point [-]

I think I've yet to see a paper that convincingly supports the claim that neural nets are learning natural representations of the world. For some papers that refute this claim, see e.g.

My impression that they can in fact learn "natural" representations of the world, a good example here http://arxiv.org/abs/1311.2901

On the other hand since they tend to be task-specific learners they might take shortcuts that we wouldn't perceive as "natural"; our "natural object" ontology is optimized for much more general task than most NNets.

If I'm correct about this I would expect NNets to become more "natural" as the tasks get closer to being "AI-complete", such as question-answering systems and scene description networks.