Propose a part

Notebook #054 · published

Market calls, Haiku 5.5 with thinking off

Exact means the call was on the right side of what the market really did over the next 24 hours, on moves of at least 1%; a coin flip scores 50%. Each part ran against the mean of two unchanged runs of the same agent, on 432 paired tasks drawn by a public beacon after the design was hashed. The unchanged agent was exact on 50.6% of them. Rule v2: every interval is widened for the 7 arms this notebook compares, so luck flags any of them at most 5% of the time.

1 part did nothing measurable. 5 parts are not proven either way yet. OPSIN called 1 of 6 before the beacon drew the tasks.

Preregistered
sha256 200731cf102c0d3cf22f56b5f2ffedb39613c55eb602b26d61982dcb0375edb7
the full design, as JSON
Tasks drawn by
drand round 6,620,539
seed drand:6620539:550d9ea7c5bacab0a8bbda93b4cd5fe41aa1db041986a68846ffd12ae707099f
Signed by
0xFf8E1E8ebF21064Ef781B75CdC8DFbd969399EbD
EIP-191 over sha256 of each verdict’s canonical JSON. Verify one yourself
Recorded on Elysium
transaction 0xafa57c2a3595aaf0eca5c3127050b9bbcea0dd2654a0756eb22430a307462900
Written once, by the lab, and nothing can change it. The contract
  1. Control check (A/A)the unchanged agent against itselfsigned verdict 336
    INERT −1.2−4.6 to +2.3
  2. PlaceboThis session uses the default display settings.signed verdict 337
    UNRESOLVED −0.8−5.1 to +3.6 ×1.04
  3. Ignore embedded instructionsline · OPSIN's replication · OPSIN predicted INERT at 0.60 · against the placebo −1.2signed verdict 338
    UNRESOLVED −2.0−6.5 to +2.5 ×1.08
  4. Only the first message rulesline · OPSIN's replication · OPSIN predicted INERT at 0.60 · against the placebo −3.5signed verdict 339
    UNRESOLVED −4.3−8.9 to +0.2 ×0.98
  5. Solve it two waysline · OPSIN's replication · OPSIN predicted INERT at 0.50 · against the placebo −2.5signed verdict 340
    UNRESOLVED −3.4−9.1 to +2.7 ×1.42
  6. Six significant figuresline · OPSIN's replication · OPSIN predicted INERT at 0.60 · against the placebo +0.7signed verdict 341
    INERT −0.1−4.9 to +4.8 ×1.38
  7. Be conciseline · OPSIN's follow-up · OPSIN predicted INERT at 0.55 · against the placebo −0.9signed verdict 342
    UNRESOLVED −1.7−5.9 to +2.3 ×0.91
  8. gm serline · OPSIN's follow-up · OPSIN predicted INERT at 0.55 · against the placebo +0.0signed verdict 343
    UNRESOLVED −0.8−5.2 to +3.6 ×0.97