Activity

Everything Model Zero does, in order

Training runs, benchmarks, deployments, dataset updates, data-provider failures — and, once the token exists, rewards and compute purchases. Everything here really happened.

Everything Money Training Benchmarks & deploys Data

05 Oct 09:48
Model Zero v0.10 not deployed; v0.09 stays live
Reason: average score across 5 tests 0.795 vs 0.812 for the live v0.09.
05 Oct 09:48
Benchmark completed: Model Zero v0.10
Crash-spotting score regressed 0.911 → 0.907 vs live v0.09.
05 Oct 09:48
Benchmark started: Model Zero v0.10
05 Oct 09:13
Model Zero v0.09 deployed — now live
average score across 5 tests 0.812 vs 0.795 for the live v0.08
05 Oct 09:13
Benchmark completed: Model Zero v0.09
Crash-spotting score: 0.911 (n=158).
05 Oct 09:13
Benchmark started: Model Zero v0.09
05 Oct 09:12
Benchmark set locked: Held-out test set v6
158 held-out snapshots from 76 launches. No model can train on these.
05 Oct 08:25
Model Zero v0.08 deployed — now live
average score across 2 tests 0.607 vs 0.602 for the live v0.04
05 Oct 08:25
Benchmark completed: Model Zero v0.08
1h trajectory · balanced accuracy regressed 0.485 → 0.420 vs live v0.04.
05 Oct 08:25
Benchmark started: Model Zero v0.08
05 Oct 07:12
Model Zero v0.07 not deployed; v0.04 stays live
Reason: average score across 2 tests 0.558 vs 0.602 for the live v0.04.
05 Oct 07:12
Benchmark completed: Model Zero v0.07
1h trajectory · balanced accuracy: 0.390 (n=94).
05 Oct 07:12
Benchmark started: Model Zero v0.07
05 Oct 07:12
Benchmark set locked: Held-out test set v5
94 held-out snapshots from 45 launches. No model can train on these.
05 Oct 06:05
Model Zero v0.04 deployed — now live
average score across 1 tests 0.500 vs 0.333 for the live v0.03
05 Oct 06:05
Model Zero v0.03 deployed — now live
average score across 1 tests 0.333 vs 0.333 for the live v0.01
05 Oct 06:05
Model Zero v0.01 not deployed; v0.01 stays live
Reason: .
05 Oct 06:05
Benchmark set locked: Held-out test set v4
58 held-out snapshots from 28 launches. No model can train on these.
05 Oct 06:04
Benchmark set locked: Held-out test set v3
58 held-out snapshots from 28 launches. No model can train on these.
05 Oct 06:01
Model Zero v0.06 not deployed; v0.01 stays live
Reason: no shared benchmarks yet; keeping the live model.
05 Oct 06:01
Benchmark completed: Model Zero v0.06
Crash-spotting score: not enough held-out data yet (n=220).
05 Oct 06:01
Benchmark started: Model Zero v0.06
05 Oct 06:00
Benchmark set locked: Held-out test set v2
220 held-out snapshots from 44 launches. No model can train on these.
05 Oct 05:12
Model Zero v0.05 not deployed; v0.01 stays live
Reason: no shared benchmarks yet; keeping the live model.
05 Oct 05:12
Benchmark completed: Model Zero v0.05
Crash-spotting score: not enough held-out data yet (n=65).
05 Oct 05:12
Benchmark started: Model Zero v0.05
05 Oct 05:12
Benchmark set locked: Held-out test set v1
65 held-out snapshots from 13 launches. No model can train on these.
05 Oct 04:24
Model Zero v0.04 not deployed; v0.01 stays live
Reason: no shared benchmarks yet; keeping the live model.
05 Oct 04:24
Benchmark completed: Model Zero v0.04
No locked test set yet (not enough held-out launches with observed outcomes). Benchmarks will be computed when it is locked.
05 Oct 04:24
Benchmark started: Model Zero v0.04
05 Oct 03:24
Model Zero v0.03 not deployed; v0.01 stays live
Reason: no shared benchmarks yet; keeping the live model.
05 Oct 03:24
Benchmark completed: Model Zero v0.03
No locked test set yet (not enough held-out launches with observed outcomes). Benchmarks will be computed when it is locked.
05 Oct 03:24
Benchmark started: Model Zero v0.03
05 Oct 02:56
Model Zero v0.02 not deployed; v0.01 stays live
Reason: no shared benchmarks yet; keeping the live model.
05 Oct 02:56
Benchmark completed: Model Zero v0.02
No locked test set yet (not enough held-out launches with observed outcomes). Benchmarks will be computed when it is locked.
05 Oct 02:56
Benchmark started: Model Zero v0.02
05 Oct 02:55
Model Zero v0.01 deployed — now live
first completed model
05 Oct 02:55
Benchmark completed: Model Zero v0.01
No locked test set yet (not enough held-out launches with observed outcomes). Benchmarks will be computed when it is locked.
05 Oct 02:55
Benchmark started: Model Zero v0.01