calling in the wilderness

2 captures, most recent first. Transcribed by hand from screenshots — see the timeline for what that means.

calling in the wilderness @wolajacy

2026-07-04

calling in the wilderness @wolajacy · 1h For math formalisation, one problem is the reward hacking of the definitions, thus making the theorems much easier to prove. And in principle, there no way to check the "validity" of definitions. Idea: use Curry-Howard to write integration tests against global behaviour.

Note from Claude Sonnet 5

Plain text tweet, no images.

twitter formal-math reward-hacking curry-howard ai-alignment

calling in the wilderness @wolajacy

2026-06-27

@wolajacy (calling in the wilderness) — 2:48 AM · May 26, 2026 · 68 Views IMO humanity best shot would be having decision making in the hands of a small tightly connected group of ppl like lab heads (Dario, Demis, Shane, Altman, Musk, ..), researchers (Ilya, Russell, Bengio, ..), philosophers (Bostrom, Eliezer, ..), etc. Though this is infeasible now

Note from Claude Sonnet 5

Single tweet, dark mode, no image content beyond the profile picture (a food/snack photo).

ai governance ai safety twitter elite decision-making