| Age | Commit message (Expand) | Author |
|---|
| 2026-08-30 | E8 launch order: armB (longest) first, then A/C/D1/D2/D3HEADmain | Void Agent |
| 2026-08-29 | optimize E8: precompute causal mask buffer, add eval early exit, and enable c... | CaptainJack2491 |
| 2026-08-29 | implement Addendum 8: 6-arm token-space recurrence suite (arms A, B, C, D1, D... | CaptainJack2491 |
| 2026-08-25 | E7 relaunch order: GPU cell first, completed tf-wd01 cell last (idempotent skip) | Void Agent |
| 2026-08-21 | E7 jobs: 4M-step long-horizon, mixed-device (rnn->cpu, transformer->cuda+comp... | Void Agent |
| 2026-08-17 | E6 jobs: 16 cells [2,1000] K=32 cuda AMP (14 primary + 2 batch-128 ablation);... | Void Agent |
| 2026-08-16 | phase3: task_mode (is_prime), train_frac, lr_decay flags + tests (41 green); ... | Void Agent |
| 2026-08-15 | E2 wd sweep: 8 jobs (0.01/0.1/0.3/3.0 x both models, seed 0; 1.0 = existing c... | Void Agent |
| 2026-08-15 | speedup: batched eval (46x, sieve-stub verified), run_sweep orchestrator (2-w... | Void Agent |
