← back to timeline

EXP-CA-EVO-PILOT

pending

CaEvo pilot — CA substrate + LLM evaluators + evolutionary selection

2026-04-30 L6 level paper5 1 runs $0.01
new
premortem
mock
real
metrics
analyze
review
krit
done

In plain language

This experiment uses Conway's Game of Life as a source of new patterns, with AI models acting as judges to score how interesting these patterns are. The researchers are trying to see if this setup can create novel patterns that are different from what the AI models have seen before, by evolving the starting patterns based on the AI's scores. It is still unclear whether the AI judges will consistently find new patterns interesting over time, or if they will simply repeat familiar ideas.

Technical details

Research hypothesis

Paper4 (exp-evo-loop-pilot) showed DECLINING novelty trajectory when LLM is the substrate. This pilot tests the complementary architecture: Conway's Life as substrate, LLM agents as evaluator panel, evolutionary selection on CA seeds. CA has genuine computational irreducibility — novelty source is outside LLM training distribution. LLM evaluates but does not generate. Falsifiable prediction: if LLM interestingness scores CLIMB across generations (agent consensus improves), external-substrate + LLM-evaluation unlocks novelty that LLM-as-substrate cannot. If scores plateau/decline: LLM evaluator itself is retrieval-bounded (evaluates against same training templates regardless of CA).

Experimental setup

Type: simple

Condition Parameters
CA_EVO_NOVELTY persona: IDENTICAL, n_runs: 1

Factors: selection (NOVELTY)

Parameters

n_agents
4
model
google/gemini-2.5-flash-lite
temperature
0.7
ca-substrate llm-evaluator evolutionary-loop sakana-asal-replication paper5-foundational