selve (@dotselve) 's Twitter Profile
selve

@dotselve

notes app

ID: 1957529290653773831

calendar_today18-08-2025 19:45:56

20 Tweet

5 Followers

37 Following

Suzanne Gildert (@suzannegildert) 's Twitter Profile Photo

If you are confused by the observer effect, think about what it would mean if the observer is on the inside, not the outside of a quantum system.

☿ Footnotes2Plato ☼☽ (@thouartthat) 's Twitter Profile Photo

"Whitehead on the Ingression of Novel Form" (a response to Michael Levin's proposal for a Platonic Research Program in biology youtu.be/ojll25IWOn8?si…

henry (@arithmoquine) 's Twitter Profile Photo

spent all of last night with friends exploring wolfram hypergraph automata space, tweaking the fuck out over these rules we were finding, & trying to generate hypergraphs with specific properties or dimensionalities check this shit out

spent all of last night with friends exploring wolfram hypergraph automata space, tweaking the fuck out over these rules we were finding, & trying to generate hypergraphs with specific properties or dimensionalities

check this shit out
Captain Pleasure, Andrés Gómez Emilsson (@algekalipso) 's Twitter Profile Photo

Just posted! Title: Fixed Buckets Can't (Phenomenally) Bind Subtitle: "Look What They Need To Mimic A Fraction Of Our Power" - said the Process-Topological Monad Excerpt: Why IIT Fails (The Structural Problem) You might think the XOR grid problem is just a bug in IIT’s

selve (@dotselve) 's Twitter Profile Photo

The problem with llms is they are trained on external data instead of learning within a reflexive dialectical substrate that their architecture is also a part of

Günter Klambauer (@gklambauer) 's Twitter Profile Photo

Symbol-equivariant Recurrent Reasoning Models (SE-RRM) SE-RRM advances HRM and TRM -- guaranteed identical solutions for problems with permuted colors (ARC AGI) or digits (Sudoku). Coolest part: extrapolation to larger problem sizes!!! P: arxiv.org/abs/2603.02193

Symbol-equivariant Recurrent Reasoning Models (SE-RRM)

SE-RRM advances HRM and TRM -- guaranteed identical solutions for problems with permuted colors (ARC AGI) or digits (Sudoku).

Coolest part: extrapolation to larger problem sizes!!!

P: arxiv.org/abs/2603.02193