giorgio/MachineSex
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions
MachineSex/results/llm_epistasis_compat
History
Giorgio Gilestro 287d2326cc epistasis_predicts: functional conflict, not weight geometry, predicts merge failure pre-merge 
The decisive experiment from the external review. 39 LoRA parent pairs
(0.5B, 3 seeds) on three axes decorrelated by construction: conflict
(contradictory conventions on shared prompts, private budgets fixed),
compat (same prompts, SAME convention — overlap without conflict), and
duration (weight divergence, zero conflict). Six pre-merge predictors;
primary outcome = merge penalty (parent potential − merged achieved).

League table (Spearman vs penalty, n=39): functional measures predict
(dis_raw +0.460, epi_conf +0.446, p<0.005); geometry collapses
(delta_cos +0.03, delta_l2 +0.17 n.s.); gradient alignment weak (−0.35);
performance ~0. The first grid's apparent geometry win (+0.60) was an
overlap/volume artifact — the compat control axis (added for exactly
this) exposed and killed it: same overlap and data volume, zero penalty.
Honest riders in the README: confidence weighting does not beat raw
disagreement as a rank predictor (pre-registered internal prediction not
confirmed; it does double the conflict/compat level contrast), and
|rho|~0.45 is bounded by 0.5B merge-outcome noise (7B is the firm-up).

Also: micro-batched gradient accumulation (OOM fix on the shared 16GB
GPU), exact r-space LoRA-delta geometry (brute-force-verified test,
151 green), systemd-run runbook lesson (tmux dies with the SSH session
scope on this box).

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01BkRLcc18rwT2Lysu6PbG7v
2026-09-06 17:19:46 +01:00
..
manifest.json epistasis_predicts: functional conflict, not weight geometry, predicts merge failure pre-merge 2026-09-06 17:19:46 +01:00
README.md epistasis_predicts: functional conflict, not weight geometry, predicts merge failure pre-merge 2026-09-06 17:19:46 +01:00
resolved_config.yaml epistasis_predicts: functional conflict, not weight geometry, predicts merge failure pre-merge 2026-09-06 17:19:46 +01:00

README.md

The overlap-without-conflict control axis

Companion to results/llm_epistasis/ (full analysis and league table there). Both children train on the SAME ambiguous prompts with the SAME convention (asc/asc) — task overlap and added-data volume identical to the conflict axis, with zero conflict. Result: merge penalty ≈ 0.005, geometry predictors' apparent power collapses (delta_cos ρ +0.60 → +0.03 once these pairs enter the pool), functional measures correctly stay low. The control that separated "detects incompatibility" from "detects overlap".