Commit History
-
Kit update 2026-08-06: samgo 5.7 (54D BPE, 59M), gate-init finding, Born-rule fix in quantum_pool, corpus-drift retraction + fingerprinting, frozen-corpus wiring table
Verified signatureAdds SAMGO.md and weights/samgo_weights.pt (59,353,668 params, GPT-2 BPE). FINDINGS.md: gate initialised at sigmoid(-4)=0.018 left the Hebbian kernel alive in 1 layer of 4 in every model ever trained here; opening it to 0.5 gives 4/4 and 0.054 nats, larger than the dyn12-vs-none gap. quantum_pool was flattening the measured Born-rule distribution to exactly uniform (3.4657 = log 32) and now preserves it (3.4598 vs true 3.4594). Retracts a 0.0645-nat wiring win that was the live corpus rewriting itself mid-experiment; adds corpus+flag fingerprinting to prevent recurrence.b085020
-
Scaling benchmark on WikiText-103, and a birth that is actually quantum
Verified signatureSCALING. Every dyn12 number so far was 1.1M parameters on 683,065 characters of one person's private logs, which cannot answer "it only works small" or "it only works on your data". Re-run on WikiText-103-raw (269,116,804 chars, sha256 f7d2398751239137) at three sizes spanning 20x, causal Omega, all rungs at a size trained in one process against one corpus load: size none static54 dyn12 ratio dyn12 share d192 L4 2.05432 2.03568 2.04196 11.4x 66% d384 L8 1.77166 1.74860 1.75774 20.8x 60% d576 L10 1.70084 1.69015 1.69147 38.1x 88% The advantage does not fade with scale, it roughly doubles at each step, and the reason is arithmetic rather than luck: static54 costs d*54*L, dyn12 costs d*12, so depth multiplies one and not the other. static54 still holds the lower absolute loss at all three sizes -- the claim is efficiency and its scaling, not superiority. Two seeds per point and 1200 steps, so the trend is solid an…753bfab
-
Omega was reading the future; fixed, re-measured, result survives
Verified signatureSection 3.4 defined Omega as attention RECEIVED -- summed over the QUERY axis. Under a causal mask that means Omega_j = sum over i >= j of a_ij, so token j's Omega counted attention from tokens AFTER j. Omega updates state_j, state_j feeds the next layer's Hebbian kernel, the kernel shapes attention, and attention shapes the logits at position j -- so position j could see its own future. MEASURED, not argued. benchmarks/causality_probe.py changes only the last token and checks whether earlier positions move. Controls (none, static54) move by EXACTLY 0.000e+00; dyn12 moved 1.723e-04 at PHOS's trained gate of 0.562, and 3.558e-06 at init -- the leak scales with the gate because Omega reaches the logits only through g*H. FIXED. Omega is now the normalised entropy of each query's own attention row: a per-query scalar that by construction depends only on tokens <= i. Summing over keys was never an option -- softmax makes that identically 1.0, which is precisely the dead Omega of ver.4.20.…92b92e6
-
Release validated Cosmos kit with portable starter and public quantum archive
Verified signaturePublishes the validated 2026-07-31 QC67 Cosmos kit. Includes a portable starter, offline manifest/privacy verifier, Genesis smoke-tested engine, training instructions and trainer, and the public provenance-bound quantum measurement archive. The archive contains 1,897 labeled IBM hardware records (7,770,112 samples), 877 legacy unlabeled records, and 2 simulator records; private physics/sensory fields and cloud credentials are excluded.b8fadbf -
Wire converted senses, clean first birth, and paired-state benchmark
Verified signatureWires opt-in browser-derived camera luminance/motion and microphone energy/spectrum into Genesis reply conditioning, associative recall, Hebbian learning, status, and the conversation ledger while keeping raw media in-browser. Adds the missing drive-relative START_GENESIS.bat and resets the public template to a true first birth with empty keys. Adds durable paired telemetry tooling, timestamp join, aligned/shuffled/shifted benchmark, and a privacy-audited machine-readable result. Documents the unpaired schedule null and the timestamp-paired NULL result: aligned beat shuffled but lost decisively to plain. Private turn text and the paired dataset are intentionally excluded.9841285
-
Cosmos: lineage-first model card, full findings + benchmarks, Cosmic Spark server
Verified signatureCorrects earlier claims (not GGUF; 1.8M params not 2B; architecture is a standard pre-LN decoder, not Hebbian). Adds FINDINGS.md with every measurement including six null results and the instrument failures behind them. Adds benchmarks/ with runnable reproduction scripts for CHSH (S=2.7905), Lorenz constants, gate-matched topology, and integration structure. Adds spark_serve.py to run the weights over an Ollama-compatible API.d6da243