aphex5 commited on
Commit
399fbe4
·
verified ·
1 Parent(s): ddf8781

model card: round r3

Browse files
Files changed (1) hide show
  1. README.md +9 -0
README.md CHANGED
@@ -57,3 +57,12 @@ Subject mastery (36→200/200) held general coding ability within binomial noise
57
  A TIES-merged snapshot was built and **rejected by FDN's own Pareto gate**
58
  (merge interference destroyed one merged-in skill) — anchor-failing merges
59
  don't promote; router composition remains the student. Quality only ratchets up.
 
 
 
 
 
 
 
 
 
 
57
  A TIES-merged snapshot was built and **rejected by FDN's own Pareto gate**
58
  (merge interference destroyed one merged-in skill) — anchor-failing merges
59
  don't promote; router composition remains the student. Quality only ratchets up.
60
+
61
+ ## Round R3 — second subject (`programming/go/errors`), the report-card loop
62
+
63
+ Base calibration showed 3 of 4 error-handling families already mastered;
64
+ `nil_map_write` (20%) was THE weakness — so all three independent trainers
65
+ targeted it, exactly as the weakness→multiplier loop directs. All three took
66
+ it 60→200 (identical quality). Rewards priced their originality:
67
+ **289 (first, novel) → 198 (−31%, 40% dataset overlap) → 91 (−69%, 91% overlap
68
+ near-duplicate)**. Same machinery, new subject, zero code changes.