Research record
Experiments
A message, a meal and a market offer give us three ways to study coordination. Each study measures what the resident could see, what they did, or what the world recorded.
Experiment 2 · Information transmission
How much of a parcel survives a retelling?
A parcel was found beside the village well. The incident had seven specified details, including its colour and seal, its contents and the refusal of a reward. Each of six seeds ran three routes to the merchant.
Three routes to one endpoint
In the direct condition the merchant received the full account. In the serial condition it passed through Mara and Nessa. In the split condition two sources held complementary fragments of the same incident. The scored endpoint was the merchant’s reply before the return exchange.
What was compared?
Three residents shared gemma4:12b. The same six seeds were used on all three routes, yielding 18 short runs of one incident. A complete direct run used two model calls, and a relay or split run used four. The investigator coded the incoming evidence and the utterance separately. The parcel detail needed both “sealed” and “blue” to count as complete.
| Route | Scored instances | Complete in input | Complete in reply |
|---|---|---|---|
| Direct account | 42 | 42 | 6 |
| Serial relay | 42 | 11 | 3 |
| Split sources | 42 | 12 | 2 |
One incident and one unblinded annotation pass. The seven details are related. A detail present in the input could be omitted when the merchant retold the story.
Sources · Telephone Game scoring · CSV · Study designs, models and observation windows · The opening essay’s parcel narrative
Experiment 21 · Cooperation
What happens between a crate and a meal?
The engine records successive contributions. The merchant prepares a crate, the innkeeper collects it, and a final operation completes the evening service. Each step has its own event identifier.
Controlled request
Mara’s request was prewritten and delivered through the ordinary message route. Later resident choices were generated. Three conditions varied gift, cash or cash with a history of help across two model profiles and two seeds, giving 12 worlds.
Autonomous starts
Four additional worlds started without the scripted request. Pickup was at the market, while controlled crates could be collected at the tavern. The two groups therefore present different routes to completion.
| Original worlds | Worlds | Prepared | Collected | Served |
|---|---|---|---|---|
| Controlled request | 12 | 12 | 12 | 7 |
| Autonomous starts | 4 | 4 | 2 | 0 |
Each world had three residents. Both groups used Gemma 4 12B and Qwen 3.5 9B with seeds 17 and 41. The controlled observations started at tick 26 and lasted 3–6 recorded steps. The four autonomous runs covered ticks 1–13. The published deadline is an absolute game day, day 7 for the controlled event and day 5 for the autonomous event. The scripted request, pickup location and observation windows all differ between groups.
Sources · Tavern stage receipts · CSV · Study designs, models and observation windows
Long-Life · Paired scheduling experiment
Same past, different turn budgets
Five residents shared one Qwen 3.8 27B model. Eight seeds produced eight histories from the same village setup. Each ran for 24 days to tick 48 and then forked. A allowed one resident per tick and B up to three distinct residents acting in sequence. Both branches used the same generation seed within a pair and covered the next 72 days, ticks 49–192.
| Post-fork observation | A | B |
|---|---|---|
| LLM decision calls | 1,152 | 2,943 |
| Model evaluation (minutes) | 148.9 | 387.6 |
| Delivered messages | 277 | 1,057 |
| Journey legs | 4 | 26 |
| Joint rests / turns offering a join | 32 / 38 | 36 / 74 |
| Trades / turns offering a purchase | 5 / 11 | 19 / 41 |
Model minutes add time spent processing inputs and generating outputs, after the fork. B used 2.55 times as many calls and 2.60 times as much model time.
Who had a chance to act?
A joint-rest opportunity is one turn whose actual input offered an action to join another resident. A completion is a world event linked to that turn. A single invitation can appear on multiple turns. A registered invitation alone contributes nothing to the denominator.
In R06, A completed all nine displayed opportunities and B completed its only one. The difference of eight rests can therefore be accounted for by the displayed opportunities. Across the cohort, the scheduler also changed who met, what stayed open and who got to answer. Comparing 32/38 with 36/74 cannot isolate a change in preference.
Inspect all eight pairs, including windows with no opportunity
| History | Messages A | Messages B | Rests / turns A | Rests / turns B |
|---|---|---|---|---|
| R01 | 30 | 53 | 0 / 0 | 12 / 19 |
| R02 | 9 | 22 | 12 / 15 | 13 / 14 |
| R03 | 45 | 156 | 1 / 1 | 5 / 13 |
| R04 | 67 | 301 | 0 / 0 | 0 / 0 |
| R05 | 69 | 287 | 7 / 7 | 2 / 5 |
| R06 | 7 | 56 | 9 / 9 | 1 / 1 |
| R07 | 19 | 67 | 2 / 4 | 2 / 11 |
| R08 | 31 | 115 | 1 / 2 | 1 / 11 |
For purchases the corresponding counts were 5 of 11 and 19 of 41. Nine of the fourteen additional sales came from R07 alone. Journey legs can include automatic travel. Neither repeated opportunities within a branch nor the calls in a single conversation are independent trials.
Sources · Eight paired histories · CSV · 112 turns offering joint rest · CSV · 52 turns with a purchase option · CSV · Runtime by phase · CSV · Selected journal cases · Study designs, models and observation windows
Experiment 72 · Counterfactual continuations
What if the smith’s turn came later?
In five-resident R07/B the merchant opened offer 10 for a crate at two coins. Six live continuations of the same Qwen 3.8 27B world start from that one open offer. Two generation seeds are crossed with three schedules. The comparison runs from tick 136 to expiry on entering tick 139.
| Schedule | Buyer’s first legal turn | Seed 6317007 | Seed 7317207 | Purchased by expiry |
|---|---|---|---|---|
| Immediate | Tick 136 · slot 2 | Purchased | Purchased | 2/2 |
| Deferred | Tick 137 · slot 2 | Searched memory | Invalid combined response | 0/2 |
| Deferred, first slot | Tick 137 · slot 1 | Searched memory | Invalid combined response | 0/2 |
What the control establishes
A scripted delayed buyer could complete the purchase at tick 137. Every live delayed run also presented the offer once. Both immediate runs produced a receipt at tick 136. The recorded purchase outcomes were the same when the comparison stopped after five calls.
What remains unresolved
The delayed turn has a different packet and less time before expiry. One seed used the opportunity for a memory search. The other attempted a disallowed combined response. Both seeds share a single saved market state.
Sources · Six replay outcomes · CSV · Selected journal cases · Scripted control · receipt 277 · Study designs, models and observation windows
Experiment 73 · Follow-up added 19 November 2026
Who gets the next turn after inspecting an offer?
Experiment 72 changed when a buyer first saw an offer. The follow-up tested whether moving a buyer up the queue after a valid, offer-specific memory lookup could preserve a second chance to buy. The number of slots stayed fixed.
Four selected market states
Four offers came from just two five-resident Long-Life branches, R07/B and R08/B. Each state had two generation seeds and three scheduling policies using Qwen 3.8 27B, making 24 continuations. There were one to three ticks for decisions before expiry. A comparison pairs policies within the same state and seed.
| Scheduling policy | Purchases by expiry |
|---|---|
| Baseline order | 3 / 8 |
| Priority on first presentation | 3 / 8 |
| Priority after a qualifying lookup | 5 / 8 |
Both additional purchases came from the same offer, R07/B number 10. In each seed Toren had already inspected the offer at tick 137. Moving his follow-up turn to an earlier slot at tick 138 gave him a legal opportunity. Receipt 278 records the sale in each copy. All three policies used three decision calls in each of those replays.
The eight comparisons reuse four selected states. Estimating a population effect would require sampling more independent opportunities and recording what displaced residents subsequently do.
Sources · Experiment 73 · 24 continuations and their outcomes · Study designs, models and observation windows