EXP-RNS-G1

informative

Ratchet Null (single-agent null model) — G1

2026-03-27 L6 level paper3 1 runs $0.01

new

premortem

mock

real

metrics

analyze

review

krit

done

In plain language

This experiment tested a simplified scenario with just one artificial agent to see if it could learn anything on its own. However, with only one agent and a limited number of attempts, the experiment didn't gather enough information to make any meaningful conclusions or predictions.

What we found

UNDERPOWERED (N=1): No predictions scored

Predictions we made before running

0/1 confirmed

▶ Technical details

Research hypothesis

G1 of single-agent null model. 1 agent(s) × 30 rounds.

Experimental setup

Type: single_condition

Condition	Parameters
G1_NULL	persona: PERSONA, interaction: SOLO

Factors: persona (PERSONA) × interaction (SOLO)

Parameters

n_agents: 1
n_rounds: 30
model: gemini-2.5-flash-lite
temperature: 0.9
scheduler: round_robin

Trophic Ratios by Condition

Mean trophic ratio per agent across runs. Error bars = ±1 std dev. Higher TR = more upstream (exporter).