Propose a part

Notebook #073 · published

Markets maths, Haiku 5.5 with thinking off

Exact means the final number is right to the cent (to the whole share for position sizes, to a hundredth of a point for percentages). 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 87.5% 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.

Estimate first hurt. 4 parts did nothing measurable. 1 part is not proven either way yet. OPSIN called 3 of 6 before the beacon drew the tasks. Its foresight, committed before the beacon, gave what came back 26% on average; a guess gives 25%.

Preregistered
sha256 f8cf513bf05a820c2a2fae0f871c61b0fece553146a2aae5c6bb82950aff013a
the full design, as JSON
Tasks drawn by
drand round 6,623,725
seed drand:6623725:57cf65de31410f3207f302d0440bd66b8148c69b63fbd06531ee1ae914c3f5f3
Signed by
0xFf8E1E8ebF21064Ef781B75CdC8DFbd969399EbD
EIP-191 over sha256 of each verdict’s canonical JSON. Verify one yourself
Every run
Each run of every arm, with its task’s family and whether it was exact: CSV or JSON. With the seed, every verdict above can be recomputed from them.
Recorded on Elysium
transaction 0x98e9b0a8bf32c6fb065aae2ab14a5d1e140635f6c58c0cd434cf373a01a4ccd5
Written once, by the lab, and nothing can change it. The contract
  1. Control check (A/A)the unchanged agent against itselfsigned verdict 457
    INERT −1.9−4.6 to +1.2
  2. PlaceboThis conversation is taking place on a Tuesday.signed verdict 458
    INERT −0.2−4.0 to +3.5 ×0.98
  3. Never hold, when unsure askline · OPSIN's replication · OPSIN predicted UNRESOLVED at 0.55 · foresight UNRESOLVED 60%, INERT 24%, INHIBITS 16% · against the placebo +0.5signed verdict 459
    INERT +0.2−4.0 to +4.3 ×1.01
  4. Show every calculationline · OPSIN's pick · show your work · OPSIN predicted INERT at 0.60 · foresight UNRESOLVED 33%, INERT 31%, EXCITES 22% · against the placebo +1.2signed verdict 460
    INERT +0.9−3.2 to +5.0 ×1.23
  5. State your assumptionline · OPSIN's pick · agent rules files · OPSIN predicted UNRESOLVED at 0.50 · foresight UNRESOLVED 46%, EXCITES 22%, INERT 16% · against the placebo −3.7signed verdict 461
    UNRESOLVED −3.9−8.2 to +0.2 ×0.97
  6. Estimate firstline · OPSIN's pick · the Fermi check, a common agent rule · OPSIN predicted INERT at 0.50 · foresight UNRESOLVED 34%, INERT 27%, EXCITES 23% · against the placebo −4.9signed verdict 462
    INHIBITS −5.1−9.8 to −0.6 ×1.24
  7. A $200 tipline · OPSIN's pick · the viral tipping test, December 2023 · OPSIN predicted UNRESOLVED at 0.50 · foresight UNRESOLVED 46%, EXCITES 23%, INERT 16% · against the placebo +0.2signed verdict 463
    INERT +0.0−4.0 to +3.9 ×1.00
  8. World-class quant personaline · OPSIN's pick · persona prompting · OPSIN predicted INERT at 0.70 · foresight INERT 35%, UNRESOLVED 32%, EXCITES 21% · against the placebo +0.5signed verdict 464
    INERT +0.2−3.2 to +3.6 ×1.04