site banner

Danger, AI Scientist, Danger

thezvi.wordpress.com

Zvi Mowshowitz reporting on an LLM exhibiting unprompted instrumental convergence. Figured this might be an update to some Mottizens.

10
Jump in the discussion.

No email address required.

they aren't good at synthesizing information from two fields in ways that haven't been done before

They are not good at that yet. But there are already indicators that they could become so.

  1. Midjourney will blend concepts from different places. Not just style transfer. A nice example I saw was an image of 'boy with a hedgehog'. The boy was holding a hedgehog, but also his hair was a bit spiky, like the hedgehogs. I think it is most unlikely MidJourney had ever seen a composition/juxtaposition of that kind before, and both the hedgehog and the hair were modified to make the composition work.
  2. DeepMind have AlphaZero, which plays chess, shogi and go. It plays better than human, i.e. not just based on play it has seen before, and one can argue it is crossing between different genres, not confined to one field.
  3. The often cited example of finding an analogy between compost heap and nuclear fission, again an example of crossing field boundaries.

So to say that machine learning can't synthesise information from two fields in ways that have not been done before needs more qualification, to be defensible.

A nice example I saw was an image of 'boy with a hedgehog'. The boy was holding a hedgehog, but also his hair was a bit spiky, like the hedgehogs. I think it is most unlikely MidJourney had ever seen a composition/juxtaposition of that kind before, and both the hedgehog and the hair were modified to make the composition work

You're still anthropomorphising. A more likely explanation is that there pixel patterns associated with the token "hedgehog" were detected and then reinforced in the part of the picture containing hair, due to some visual similarities between the two.