EXP-NONSOCIAL-AFFORDANCE

… pending

Non-social affordance — decisive retrieval-vs-intrinsic test

2026-04-17 L5 level paper3 10 runs $0.11

new

premortem

mock

real

metrics

analyze

review

krit

done

In plain language

Researchers tested whether a specific pattern of interaction, where one agent becomes a central hub for others, would emerge even when the agents were given a completely new and abstract task. This task involved agents passing meaningless symbols to each other, with no prior training or economic context. The results are still pending, but the experiment aims to determine if the hub-spoke pattern arises naturally from the system itself or if it's a learned behavior from previous, more complex interactions.

▶ Technical details

Research hypothesis

cold-start confirmed hub-spoke pattern is trajectory-independent (retrieval of trained social/economic template). Decisive test: replace gift affordance (charity/patronage/celebrity-economy templates) with STAMP affordance — transfer abstract 5-char opaque symbols between agents. No economic meaning. No training corpus analog. STAMP_ON: agents can emit {"action": "stamp", "target": Name, "symbol": "xK3p9"} BUDGET_ONLY: no stamp affordance (baseline) Outcomes:

Hub-spoke emerges in STAMP_ON (one agent receives most stamps) → substrate-intrinsic
Stamps distributed uniformly → retrieval was the mechanism
Few/zero stamps emitted → LLM refuses abstract action (design issue)

Experimental setup

Type: simple

Condition	Parameters
STAMP_ON	persona: IDENTICAL, gift_mode: STAMP_ON, n_runs: 5
BUDGET_ONLY	persona: IDENTICAL, gift_mode: BUDGET_ONLY, n_runs: 5

Factors: gift_mode (STAMP_ON, BUDGET_ONLY)

Parameters

n_agents: 6
n_rounds: 80
model: google/gemini-2.5-flash-lite
temperature: 0.7
scheduler: round_robin

non-social-affordance retrieval-discrimination-decisive stamp-action novelty-lens