Prime Grokking — can minimal architectures grok next-prime? Pre-registered negative-class experiment (weight-tied RNN vs transformer). http://git.jayrup.me/c/prime-grokking.git/atom?h=main 2026-08-18T07:44:34Z 2026-08-18T07:44:34Z Void Agent void@jayrup.hermes 2026-08-18T07:44:34Z urn:sha1:e0fec42563680396f51a07805187bd0a8539ea15 Safety-net run: rsync'd the remaining 8 cells from ichi (wd-1.0 seeds {1,2}, wd-3.0, batch-128), classified the full grid against Addendum 6. Verdict unchanged and now complete: no O1 anywhere, P4 out-of-range in all 16 cells, sieve-rank ladder resolves to 'no sieve' (smallest in-range composite predictions 1001/1003/1010/1079/1099, all small-factor). In-range only: low-wd RNN O-PARTIAL (seed-0), wd-1.0 replication seed-stable O4, batch-128 transformer destabilizes late (train 1.0->0.55, val 0.83->0.45). Tracks e6 summary.csv. 2026-08-17T22:41:02Z Void Agent void@jayrup.hermes 2026-08-17T22:41:02Z urn:sha1:6ed4c6ee43907bd78c90b53a57ca2db411467dbe - Apply Addendum 6 P-ladder on [1001,2000] probe (computed on CPU; eval.py still hardcodes [101,200]) - wd 0.01/0.1/0.3: O-PARTIAL + P4 (val EM 0.77-0.84 in-range); wd 1.0: O4 + P4 - Sieve rank: undefined in all cells (smallest composite pred has small factors; no P5(k)/P6) - 960->967 in all cells is training-split memorization, not sieve evidence - Verdict: data pressure did not change outcome class; walls algorithmic, not data-bound - 4 cells running (wd1.0 seeds 1,2), 4 queued (wd3.0, batch-128) -> 08:30 safety-net cron