EXP-SCARCITY-TIGHT

✓ success

Scarcity tight — budget=400, force physical-selection (paper6 step 5 follow-up)

2026-05-04 L6 level paper6 6 runs $0.04

new

premortem

mock

real

metrics

analyze

review

krit

done

In plain language

Researchers tested how limiting an agent's memory size affects its ability to survive and continue its lineage. They found that with a smaller memory, most agents died out quickly, indicating that the limited memory hindered their survival. However, in some cases, a few agents managed to survive and pass on their traits, showing a partial continuation of the lineage.

▶ Technical details

Research hypothesis

exp-scarcity-budget at 800 words gave GRACEFUL DEGRADATION (0/6 all-dead). Run 03 hint: 5 dead-rounds + depth=9 → lineage continued via survivors. Need tighter budget to test physical-selection-effect cleanly. This: budget=400 words/agent. Pre-registered: - PHYSICAL-SELECTION-EFFECT: ≥3/6 runs all-dead by gen 5 - LINEAGE-VIA-SURVIVORS: dead-runs depth ≥3 (rule lineage continued despite deaths, by ≥1 surviving agent)

PROGRAM-COLLAPSE: dead-runs depth ≤1 (no rules accepted post-death) - NO-EFFECT: still graceful at 400 (would need 200)

This is CONSTRUCT — first clean physical-selection test.

Experimental setup

Type: factorial

Condition	Parameters
SCARCITY_TIGHT	coupling: true, must_propose: true, axis_diversify: true, n_runs: 6

Factors: scarcity (tight)

Parameters

n_agents: 4
n_rounds: 100
model: google/gemini-2.5-flash-lite
temperature: 0.85

autopoiesis paper6-step5-tight genuine-scarcity physical-selection construct