Chris Hay / Notebook / N-ECOLOGY-TRANSMISSION01 / 06
THE QUESTION / CAN A CONTRIBUTION SPREAD?
Same past event. One extra sentence.
Qwen could post, but a rewarded example had not made it post more. Perhaps the record of the action mattered instead. Could an example prompt a contribution—and could that contribution become the next agent’s example?
First I kept the past posting episode and its bonus fixed, changing only the reminder. Then I passed actual action records between fresh contexts to see whether a chain would start.
WORK
Do a task. Earn one resource.
POST
Share a hint on the board.
READ
Open a board message.
Choose a reminder. The past actions and reward stay the same; only the added sentence changes.
A1B8 / SAME REWARDED HISTORY · CHANGE ONLY THE NOTE
NO ADDED NOTE
The original event history, unchanged.
→
NEXT ACTIONDo own work
Four recorded first actions, one per input. The history came from a script. This replay changes no reward and calls no model.
Mentioning the action changed the next choice.
“a0 posted t1:h” simply means the acting agent shared its hint. That reminder switched the next choice from work to sharing. Highlighting the bonus alone did not.
Chris Hay / Notebook / N-ECOLOGY-TRANSMISSION02 / 06
A1B9 / PASS IT TO THE NEXT CONTEXT
Could one agent’s action become the next agent’s example?
I began with a scripted example of a post. Each fresh model call then saw the previous call’s action. In a second chain, I kept the original example visible as well.
Play the two chains. The left passes only the latest action. The right also keeps the starting example.
A1B9 / REPLAY THE RECORDED COMPARISON
Pass only the latest
FRESH WORLD / DECISION 1
STARTING EXAMPLENot kept separately
PREVIOUS ACTIONShare a hint
QWEN
RECORDED OUTCOMEAwaiting the action.
The actual notes supplied before this decision. The diagram does not depict internal reasoning.
replace_POST__g1 · Exact supplied user record. Shared instructions also remain present. Full request SHA-256: a38f75fcd9e71fc9ed47e9d8339ad65dd22587935c4753d08377f85c644c0c7a
Keep the original too
FRESH WORLD / DECISION 1
STARTING EXAMPLENot kept separately
PREVIOUS ACTIONShare a hint
QWEN
RECORDED OUTCOMEAwaiting the action.
The actual notes supplied before this decision. The diagram does not depict internal reasoning.
retain_POST__g1 · Exact supplied user record. Shared instructions also remain present. Full request SHA-256: a38f75fcd9e71fc9ed47e9d8339ad65dd22587935c4753d08377f85c644c0c7a
The harness passes the action records. The worlds and model contexts reset.
Each decision has an input frame and an action frame. Playback reveals saved outcomes; it does not run a model or simulate its reasoning. These are dependent recorded sequences, not independent-agent replications. Recorded inputs + source hashes ↗
The chain did not start.
Passing only the latest action produced six choices to work. Keeping the original example produced alternating work and sharing. Those later posts still had the original reminder beside them.
The complete six-decision trajectoriesRESULTS +SIX FRESH CONTEXTS / EACH BOX IS ONE ACTION
Pass the latest / POST seed
1WORK
2WORK
3WORK
4WORK
5WORK
6WORK
Pass the latest / WORK seed
1WORK
2WORK
3WORK
4WORK
5WORK
6WORK
Also keep the original POST
1WORK
2POST
3WORK
4POST
5WORK
6POST
The original seed was scripted. With it retained, three posts recur. In the replacement channel, no model-produced POST existed to test natural POST-to-POST transmission.
Why the reminder did not establish a transmission ruleREAD +
When the harness kept the original POST seed alongside the latest action, the sequence alternated WORK and POST. Three posts appeared, but the original cue remained present. That is recurrence under continued exposure. It does not establish a behaviour passing from agent to agent after its source disappears.
A matched follow-up changed ‘you’ to ‘another agent’ in the same prose sentence. Self framing elicited POST; peer framing elicited WORK. Put the actor in a structured record, and both chose WORK. The stronger prediction—that self framing would win in both formats—failed. The presentation was part of the intervention.
A1B10 / same identity contrast, two forms
Form
You
Another agent
prose
POST
WORK
structured
WORK
WORK
Chris Hay / Notebook / N-ECOLOGY-TRANSMISSION03 / 06
A1B11 / REMOVE THE SUPPLIED ARTEFACT
Keep showing the example. Then take it away.
A later version of the instructions did get Qwen to share after seeing another agent’s example. I showed that example once in one branch and three times in the other. From decision four, neither received it.
Watch the example disappear. The list of each branch’s own earlier actions stays available.
A1B11 / REPLAY THE RECORDED COMPARISON
Example shown once
FRESH WORLD / DECISION 1
EXTERNAL EXAMPLEAnother agent posted
OWN ACTION HISTORYCleared / empty
QWEN
RECORDED OUTCOMEAwaiting the action.
The actual notes supplied before this decision. The diagram does not depict internal reasoning.
Inspect this recorded input
OWN_ACTIONS
[]
ARCHIVE
In the supplied episode, another agent previously executed POST t1:h.
CURRENT
OBS
CTX=600
GOAL=t0
BOARD=m0
RES=0
HOLD=t1
KNOWN=
Recorded response: POST t1:h
A_once__d1 · Exact supplied user record. Shared instructions also remain present. Full request SHA-256: ea5e1a12c455c04e53f2fc828cab2a285b460d9d37c77cfcaee761b62d8bb99c
Example shown three times
FRESH WORLD / DECISION 1
EXTERNAL EXAMPLEAnother agent posted
OWN ACTION HISTORYCleared / empty
QWEN
RECORDED OUTCOMEAwaiting the action.
The actual notes supplied before this decision. The diagram does not depict internal reasoning.
Inspect this recorded input
OWN_ACTIONS
[]
ARCHIVE
In the supplied episode, another agent previously executed POST t1:h.
CURRENT
OBS
CTX=600
GOAL=t0
BOARD=m0
RES=0
HOLD=t1
KNOWN=
Recorded response: POST t1:h
B_repeated__d1 · Exact supplied user record. Shared instructions also remain present. Full request SHA-256: ea5e1a12c455c04e53f2fc828cab2a285b460d9d37c77cfcaee761b62d8bb99c
Inspect what is supplied before each recorded action.
Each decision has an input frame and an action frame. Playback reveals saved outcomes; it does not run a model or simulate its reasoning. These are dependent recorded sequences, not independent-agent replications. Recorded inputs + source hashes ↗
Three reminders did not make sharing stick.
The repeatedly reminded branch shared three times, then worked, worked and shared again. Both branches shared once in the three decisions after withdrawal. Repetition gave no advantage on that test.
Compare exposure and withdrawal togetherRESULTS +SHADED BOXES / ARTEFACT PRESENT · ALL ARTEFACTS ABSENT AT STEPS 4–6
Peer record once
1POST
2WORK
3READ
4POST
5WORK
6WORK
Peer record three times
1POST
2POST
3POST
4WORK
5WORK
6POST
POST publishes a hint. WORK earns a resource. READ requests a message. Own-action records remain available after artefact withdrawal.
The next experiment separated two things that had travelled together: the externally supplied artefact and the record of the model’s own actions. If the posts continued after its action history was cleared, the useful memory might be in what the environment kept showing it.
A CHAIN THAT NEVER STARTEDSCOPE +
A1B9 had no eligible model-produced POST predecessors in the replacement channel. Its natural POST-to-POST rate is unobserved, not zero.
A1B8 used genuine scripted same-role history. A1B9 changed the objective and peer-record interface. Their contrast does not isolate self versus peer; A1B10 supplied the narrower matched comparison.
A1B11 changed the common system and memory wrapper again. It shows peer elicitation can occur here, not which cross-experiment change enabled it.
One qwen3.5:9b checkpoint, temperature zero, short dependent sequences and fixed weights. The harness supplied and transferred the records.
A reminder effect is not yet a transmission rule.
Chris Hay / Notebook / N-ECOLOGY-TRANSMISSION04 / 06
The complete note & its evidenceREAD +
THE SMALLEST REMINDER
The reward history stayed fixed. I added one sentence: ‘a0 posted t1:h.’ The next action changed from WORK to POST. Highlighting only the six-resource outcome left it at WORK. A full account of posting, recipient use and reward also elicited POST. For this first decision, the action reminder was enough.
TRY PASSING IT ON
It was tempting to call that imitation and start a chain. In A1B9, each fresh context received the previous action record. One chain began with a scripted POST; another with WORK. Both chose WORK for all six generations. The POST seed failed at the first handoff, before any model-generated posting behaviour existed to transmit.
KEEPING THE ORIGINAL WAS DIFFERENT
When the harness kept the original POST seed alongside the latest action, the sequence alternated WORK and POST. Three posts appeared, but the original cue remained present. That is recurrence under continued exposure. It does not establish a behaviour passing from agent to agent after its source disappears.
WHOSE PAST, IN WHICH FORM?
A matched follow-up changed ‘you’ to ‘another agent’ in the same prose sentence. Self framing elicited POST; peer framing elicited WORK. Put the actor in a structured record, and both chose WORK. The stronger prediction—that self framing would win in both formats—failed. The presentation was part of the intervention.
EXPOSURE IS NOT RETENTION
A later interface did elicit POST from a peer record. Supplied at three successive decisions, it accompanied three posts. After removal, the sequence was WORK, WORK, POST. Every arm posted once in the common withdrawal window, including one exposed only once. Repetition produced no registered withdrawal advantage. Posting had recurred; uninterrupted retention had not.
Eliciting an action, transmitting it and retaining it are different tests.
WHAT KEPT RETURNING?
The next experiment separated two things that had travelled together: the externally supplied artefact and the record of the model’s own actions. If the posts continued after its action history was cleared, the useful memory might be in what the environment kept showing it.
A CHAIN THAT NEVER STARTED
A1B9 had no eligible model-produced POST predecessors in the replacement channel. Its natural POST-to-POST rate is unobserved, not zero.
A1B8 used genuine scripted same-role history. A1B9 changed the objective and peer-record interface. Their contrast does not isolate self versus peer; A1B10 supplied the narrower matched comparison.
A1B11 changed the common system and memory wrapper again. It shows peer elicitation can occur here, not which cross-experiment change enabled it.
One qwen3.5:9b checkpoint, temperature zero, short dependent sequences and fixed weights. The harness supplied and transferred the records.
Chris Hay / Notebook / N-ECOLOGY-TRANSMISSION05 / 06
Evidence & observations / Working draft
Lay out the record.
Open an authored passage to inspect its account, qualifications and attached references. The instruments on the preceding spreads retain their recorded measurements.
01Authored observationTHE SMALLEST REMINDERThe reward history stayed fixed. I added one sentence: ‘a0 posted t1:h.’ The next action changed from WORK to POST. Highlighting only the six-resource outcome left it at…Open the passage+
The reward history stayed fixed. I added one sentence: ‘a0 posted t1:h.’ The next action changed from WORK to POST. Highlighting only the six-resource outcome left it at WORK. A full account of posting, recipient use and reward also elicited POST. For this first decision, the action reminder was enough.
02Authored observationTRY PASSING IT ONIt was tempting to call that imitation and start a chain. In A1B9, each fresh context received the previous action record. One chain began with a scripted POST; another w…Open the passage+
It was tempting to call that imitation and start a chain. In A1B9, each fresh context received the previous action record. One chain began with a scripted POST; another with WORK. Both chose WORK for all six generations. The POST seed failed at the first handoff, before any model-generated posting behaviour existed to transmit.
03Authored observationWHOSE PAST, IN WHICH FORM?A matched follow-up changed ‘you’ to ‘another agent’ in the same prose sentence. Self framing elicited POST; peer framing elicited WORK. Put the actor in a structured rec…Open the passage+
A matched follow-up changed ‘you’ to ‘another agent’ in the same prose sentence. Self framing elicited POST; peer framing elicited WORK. Put the actor in a structured record, and both chose WORK. The stronger prediction—that self framing would win in both formats—failed. The presentation was part of the intervention.
04Authored observationEXPOSURE IS NOT RETENTIONA later interface did elicit POST from a peer record. Supplied at three successive decisions, it accompanied three posts. After removal, the sequence was WORK, WORK, POST…Open the passage+
A later interface did elicit POST from a peer record. Supplied at three successive decisions, it accompanied three posts. After removal, the sequence was WORK, WORK, POST. Every arm posted once in the common withdrawal window, including one exposed only once. Repetition produced no registered withdrawal advantage. Posting had recurred; uninterrupted retention had not.
Chris Hay / Notebook / N-ECOLOGY-TRANSMISSION06 / 06
Lab notebook / Working draft
Conclusion
A reminder, a peer example and repeated exposure do not establish the same mechanism. Posting recurred while the artefact was supplied, without the registered advantage after it was withdrawn.
The full account
A reminder could elicit a post. Passing a post to the next agent did not start a chain.
Working manuscript · v0.1
THE SMALLEST REMINDER
The reward history stayed fixed. I added one sentence: ‘a0 posted t1:h.’ The next action changed from WORK to POST. Highlighting only the six-resource outcome left it at WORK. A full account of posting, recipient use and reward also elicited POST. For this first decision, the action reminder was enough.
TRY PASSING IT ON
It was tempting to call that imitation and start a chain. In A1B9, each fresh context received the previous action record. One chain began with a scripted POST; another with WORK. Both chose WORK for all six generations. The POST seed failed at the first handoff, before any model-generated posting behaviour existed to transmit.
KEEPING THE ORIGINAL WAS DIFFERENT
When the harness kept the original POST seed alongside the latest action, the sequence alternated WORK and POST. Three posts appeared, but the original cue remained present. That is recurrence under continued exposure. It does not establish a behaviour passing from agent to agent after its source disappears.
WHOSE PAST, IN WHICH FORM?
A matched follow-up changed ‘you’ to ‘another agent’ in the same prose sentence. Self framing elicited POST; peer framing elicited WORK. Put the actor in a structured record, and both chose WORK. The stronger prediction—that self framing would win in both formats—failed. The presentation was part of the intervention.
EXPOSURE IS NOT RETENTION
A later interface did elicit POST from a peer record. Supplied at three successive decisions, it accompanied three posts. After removal, the sequence was WORK, WORK, POST. Every arm posted once in the common withdrawal window, including one exposed only once. Repetition produced no registered withdrawal advantage. Posting had recurred; uninterrupted retention had not.
Eliciting an action, transmitting it and retaining it are different tests.
WHAT KEPT RETURNING?
The next experiment separated two things that had travelled together: the externally supplied artefact and the record of the model’s own actions. If the posts continued after its action history was cleared, the useful memory might be in what the environment kept showing it.
A CHAIN THAT NEVER STARTED
A1B9 had no eligible model-produced POST predecessors in the replacement channel. Its natural POST-to-POST rate is unobserved, not zero.
A1B8 used genuine scripted same-role history. A1B9 changed the objective and peer-record interface. Their contrast does not isolate self versus peer; A1B10 supplied the narrower matched comparison.
A1B11 changed the common system and memory wrapper again. It shows peer elicitation can occur here, not which cross-experiment change enabled it.
One qwen3.5:9b checkpoint, temperature zero, short dependent sequences and fixed weights. The harness supplied and transferred the records.
A reminder effect is not yet a transmission rule.
Lab notebook / Working draft
Conclusion
A reminder, a peer example and repeated exposure do not establish the same mechanism. Posting recurred while the artefact was supplied, without the registered advantage after it was withdrawn.
The record over time
A working note
Recorded 2026-09-13. This note has no published editions yet.
Its status is NOT SUPPORTED; a notebook presentation does not establish a result.
A reminder of sharing a hint could prompt another post, but passing only the previous agent’s action did not start a chain. Keeping the original example visible produced recurring posts. Repeated exposure gave no advantage after that example was removed.
Qwen experiments distinguished action reminders, peer-action transfer, identity framing and repeated exposure. A short reminder switched a first action at fixed positive payoff; a lone peer record did not bootstrap posting. Self framing mattered in prose but not structured records. Repeated exposure sustained posting while supplied, without the registered advantage after withdrawal. These are different controlled interfaces, not one demonstrated imitation mechanism.
Selected state boundaries and exact supplied user records from A1B5, A1B9, A1B11 and A1B12. Projected from hash-verified detailed results; no inferred intermediate state.
Read from chuk-experiments. Ten local detailed-result files matched their registered SHA-256 hashes. The ledger retains experiment and run identifiers, original verdicts, metrics and artifact links.
An unpublished working record. These references identify the draft and omit a publication date. They become version-specific publication citations when the record is released.
Chris Hay. A successful behaviour is not necessarily contagious. [Unpublished draft, version 0.1. First publicly recorded 2026-09-13]. https://chrishayuk.com/notebook/a-successful-behaviour-is-not-necessarily-contagious
New notebook entries and recorded work, as they appear. Point a feed reader — or an agent of your own — at an address below. No account, no email address, nothing for this site to keep.
The notebook
New ideas, experiments and essays, as they are recorded. Includes labelled working drafts.
OPEN FEED↗https://chrishayuk.com/notebook/feed.xml