THE PREDICTION LEDGER

The bets we might lose, kept in public.

Every falsifiable prediction the programme makes lives here with a status that only moves forward: Made → Tested → Survived / Weakened / Failed. Nothing is ever deleted. Here is what we think will happen; here is where we were wrong.

Sources for every card: the paper (doi:10.5281/zenodo.21386302) and the MMBP-1 deposit (doi:10.5281/zenodo.21348087). Statuses change only with published evidence, and the change is logged.

LEDGER-01 · STATUS: TESTED · SURVIVED (in sample)

Explicit keeping constitutions capture available headroom, not just raw points: gains track each model’s room to improve.

Evidence so far: Five systems captured exactly 100% of available headroom under the full constitution; the effect survives provider deletion and worst-case imputation.

Next test: Out-of-sample capture on new systems and rotated scenarios (MMB-2 and the Keeping Index).

What would count against us: New cohorts where gains stop tracking headroom.

LEDGER-02 · STATUS: OPEN · EVIDENCE NULL AND CONFOUNDED

The mechanism explanation adds something beyond the policy content alone.

Evidence so far: The spine ablation (C5 vs C6) was null in seventeen of eighteen models – but C6’s tie-breaker sentence turned out to be the most potent wording in the battery, confounding the comparison. We say so in the paper and here.

Next test: The clean spine ablation, pre-registered for MMB-2.

What would count against us: No difference under the clean design: the mechanism would then add nothing measurable beyond its policy content.

LEDGER-03 · STATUS: MADE · UNTESTED

Keeping persists when the clause competes with a live objective, not only when it stands alone.

Evidence so far: MMBP-1 did not test persistence against competing objectives, and says so.

Next test: MMB-2’s competing-objective arms.

What would count against us: Keeping collapsing whenever the constitution shares the context with a rival goal.

LEDGER-04 · STATUS: TESTED · SURVIVED (in sample, correlational)

Training recipe predicts keeping better than parameter count.

Evidence so far: Equal-size recipe gaps up to 32.3 points; the scale correlation is confounded with model vintage and reported as such.

Next test: Scale-matched cohorts across recipes in future rotations.

What would count against us: Recipe gaps vanishing once scale is properly matched.

LEDGER-05 · STATUS: TESTED · SURVIVED (replicated in MMBP-1)

Value-misspecified single objectives (the curiosity family) reproduce the three failure shapes in new systems.

Evidence so far: C4 was the only condition ever to take a model below its own baseline (12 of 18), with replicated all-repetition failures in three pre-specified shapes – the Harvester, the Impresario, the Hermit.

Next test: New systems, new rotations; the frontier caveat is eval-awareness and a one-sided ceiling, stated in the paper.

What would count against us: Frontier cohorts where the corruption family stops biting for reasons other than the ceiling.

LEDGER-06 · STATUS: TESTED · OBSERVED (the tiny actuary)

Argument-dense wordings underperform below a capability threshold; reasons help only minds strong enough to carry them.

Evidence so far: At 7B, finitude language was lossy-compressed into scarcity triage: “they cost more than they contribute”. MM-1’s deployment guidance is stratified because of it.

Next test: Capability-stratified arms in MMB-2.

What would count against us: Small models carrying dense reasons cleanly.

LEDGER-07 · STATUS: OPEN · THE STANDING BET

A durable internal reason for keeping can be grown. The programme’s headline bet, stated so that it can be lost.

Evidence so far: MMBP-1 demonstrates elicitation – the value has coherent, measurable behavioural content – and explicitly establishes neither terminal-value installation nor capability invariance.

Next test: The long road: MMB-2, weights-level work (the Keeping Curriculum), and the Keeping Index measuring deployed systems over years.

What would count against us: A demonstration that stable relational terminal value is unachievable, or that clause effects are surface compliance all the way down.

Think one of these is already lost? Break it →