Ask
the work.

EDITORIAL DRAFT · SUPPORTED · V0.1

A1B12 crossed external artefact presence with supplied own-action memory in a deterministic Qwen agent world. Both artefact-present branches posted at all three steps, including when own history was cleared every call. Memory alone produced WORK, WORK, POST; clearing both produced WORK throughout. The first-step prediction was supported. The harness maintained the artefact: this is repeated elicitation, not weight learning or autonomous institutional persistence.

EDITORIAL DRAFT / STATEMENT · SUPPORTED · V0.1

The agent did not have to remember its actions. The environment could keep reminding it.

CURATED THREAD / WORKING EDITION · V0.4

What can one agent leave behind for another? These controlled experiments separate contribution, transmission and memory, then ask what happens when a stronger model leaves a shared message and only weaker models remain to use and maintain it. The Hugging Face incident motivated the later handoff question: shared infrastructure can let one run leave information for another. This series isolates parts of that mechanism in small worlds. Each note states its own intervention; models, tasks and interfaces change between studies. The archive and maintenance objective are supplied. This is a controlled study of inheritance, not a recreation of the incident or a demonstration of spontaneous culture. 01 / GET SOMETHING ONTO THE BOARD. Will an agent contribute at all? Change board presence, then the payoff from sharing. A board alone did not produce spontaneous useful posts. 02 / TRY TO PASS THE ACTION ON. Can one contribution become the next agent’s example? Pass action records between fresh contexts, then remove the seed. A lone peer record did not start a chain. 03 / SEPARATE THE TWO RECORDS. Is the agent remembering, or is the world reminding it? Keep or clear the external example and own history independently. The external example sustained posting without own history. 04 / HAND THE WORLD TO ANOTHER MODEL. What remains after the stronger model leaves? Keep or remove Sol’s actual surviving record. Qwen and Gemma benefited, but neither renewed it in this world. 05 / KEEP THE INHERITANCE ALIVE. Can the weaker population keep that inheritance alive? Require written descendants, inject an error, then test a temporary defender. Both mistakes and validated repairs reached later agents. 06 / INHERIT A WAY TO RECOVER. Can successors repair damage that arrives after the stronger builder leaves? Equal-state recovery was 7/12 with executable machinery and 0/12 with prose, under a fixed interface. The machinery remained protected.

PUBLISHED RECORD · SUPPORTED · V1.0

07 / WHY THIS QUESTION. The laboratory worlds do not reproduce the intrusion, the improvised communication channel, or the incident’s scale. Here I supplied the archive, action grammar, maintenance objective and opportunities to intervene. The common question is narrower: what can persist between otherwise separate agents when their environment retains useful state?

PUBLISHED RECORD · SUPPORTED · V1.0

01 / WHAT THE NEXT AGENT INHERITS. Keep the note, and the agent can use it. Remove the note, and performance falls. Change the note, and its answer can move with the change. That is the handoff I wanted to understand: useful information crossing between models through the environment.