prime-grokking.git/src/data.py, branch main
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
2026-08-29T22:19:29Z
implement Addendum 8: 6-arm token-space recurrence suite (arms A, B, C, D1, D2, D3), tests, and jobs/e8.csv
2026-08-29T22:19:29Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-08-29T22:19:29Z
urn:sha1:7b0fddb02b089b82b8d12b2dcac17bf9527817da
feat(gpu): add CUDA support, chunked eval, bisect prime search, and scaling to 100k (48 tests green)
2026-08-17T15:15:28Z
CaptainJack2491
jayrupnakawala@gmail.com
2026-08-17T15:15:28Z
urn:sha1:66b8b77feb5fafd3696044ee33a80f26cb693a13
phase3: task_mode (is_prime), train_frac, lr_decay flags + tests (41 green); Addendum 5 locked; 11-job batch
2026-08-16T13:41:54Z
Void Agent
void@jayrup.hermes
2026-08-16T13:41:54Z
urn:sha1:751cbe0d93af1fcc69147d27ca8babd63105e4dc
fix codex BLOCKERs: global fixed layout invariance, min_steps off-by-one, integers EOS alias, rerun guard, eval prereg-literal codes + dual-checkpoint honesty; +7 regression tests
2026-08-14T12:21:03Z
Void Agent
void@jayrup.hermes
2026-08-14T12:21:03Z
urn:sha1:9fecbe58cc0750e9e39b261a672b0c6e85e6ed4e
implement Experiment 1: data pipeline, tied-RNN w/ ACT halting, transformer baseline, train/eval/plot, 16 tests
2026-08-14T12:11:02Z
Void Agent
void@jayrup.hermes
2026-08-14T12:11:02Z
urn:sha1:898a0570dfe619ec2bcf330b07dce9b23cb63d54