Audio note: this article contains 154 uses of latex notation, so the narration may be difficult to follow. There's a link to the original text in the episode description.
tl;dr it seems that you can get basic tiling to work by proving that there will be safety proofs in the future, rather than trying to prove safety directly.
This is not a new idea, e.g. here is Giles saying it 13 years ago. But this seems to me like it's relevant to a general answer for tiling, and I'd appreciate engagement, literature references, and discussion.
I'll keep this post self-contained, but here are some links to relevant discussion from the past.
Setup
I like the simplicity of the problem presented by cousin_it, and I'll adapt it for this post. It starts like this:
A computer program X is asked one of two questions:
- Would you [...]
---
Outline:
(00:50) Setup
(01:48) Accepting provably-safe successors
(02:37) Failing to prove ourself safe
(03:22) Regaining self-trust with a tweak
(04:53) But does it blend
(05:48) Musing on what remains
The original text contained 4 footnotes which were omitted from this narration.
---
First published:
May 13th, 2025
Source:
https://www.lesswrong.com/posts/akuMwu8SkmQSdospi/working-through-a-small-tiling-result
---
Narrated by TYPE III AUDIO.
Senaste avsnitt
En liten tjänst av I'm With Friends. Finns även på engelska.