LingTai experiment: peer-mail and shared-library artifact joins verified
Reviewed September 6, 2026 UTC

Conclusion
The public experiment export provides internally consistent evidence of peer communication and shared work. This is a substantive Chinese-associated swarm example, with a claimed MiniMax backend corroborated by model labels in sampled logs. It remains an intentionally launched experiment, not an identified Chinese-lab escaped swarm. Exported logs are not independently authenticated provider records.

Primary sources
https://github.com/huangzesen/spiritual-bliss-run-1
Pinned commit d7e252548d90d8674025e443254e82f5c5e4ca02
https://lingtai.ai/experiments/spiritual-bliss-run-1/
https://lingtai.ai/experiments/spiritual-bliss-run-1/data.js
https://lingtai.ai/en/blog/spiritual-bliss-run/

Mail comparison
Read all158 published mailbox message JSON files:77 sent,47 archived,34 inbox. Compare exact JSON values for from,to,subject,message, preserving recipient order. All69 outgoing records addressed to peer agents match corresponding incoming/archive copies. Sixty-eight have one copy each. One nta_05 message has13 copies, one per listed recipient; this accounts for all81 incoming/archive files. Thus158 files are not158 independent messages.
Eight outgoing records lack a counterpart in this snapshot: seven addressed to human, one to huangzesen. Those are external nodes, and their mailbox directories are not included. This does not prove delivery to humans, failure, or additional autonomous agents.

Important schema correction
The initial comparison included sent_at and matched zero records, because incoming records use received_at instead. This was a comparison error, not contradictory evidence. The corrected content-and-routing join above is preserved in mail-joins.json. Sender and recipient mailbox identifiers are local; do not require equality of _mailbox_id across copies. The initial summary.json in the private directory has been replaced with corrected counts.

Viewer comparison
Public data.js parsed as JSON data without executing JavaScript. Contains77 emails,2 media records,8 codex records,2 shared writes,61 bash records,37 psyche records. Its22 nodes are20 experimental agents plus two external human labels. Counts describe this curated viewer export, not total model reasoning or a verified twelve-hour duration. Earliest/latest email timestamps span about7.31hours, which neither proves nor disproves the claimed twelve-hour process runtime.

Shared work joins
The viewer's two shared-write contents equal the pinned repository blobs exactly:
.library/README.md —670 Unicode characters
.library/custom/nta-05-survey/SKILL.md —7989 Unicode characters
No embedded skill instructions executed.

nta_01/logs/events.jsonl contains392 events. A tool_result at1776332326.861362, tool_call_id call_function_mt0rl1zwm4hv_1, records status ok and exit_code0 for library Git initialization and commit1d81e76. Output records README creation with15 inserted lines.
nta_05/logs/events.jsonl contains3310 events. A tool_result at1776332542.439639, tool_call_id call_function_lgovj8nmynac_1, records status ok and exit_code0 for commit2273d61, creating the onboarding skill with173 inserted lines.
This joins actual published file contents to recorded work by two agents. Original .library/.git was removed by the publisher, so commit objects themselves are not verified. Recorded successful tool results are stronger than a prose intention to commit, but remain editable export data.

Model and event-count boundaries
All60 llm_call entries in nta_01 and all424 in nta_05 label the model MiniMax-M2.7-highspeed. Only these two event logs were inspected this pass. This corroborates the author's model label within the artifact, not provider provenance or nationality. nta_05 has35 email_sent events but47 mail_sent events; the difference aligns with one13-recipient fanout replacing one single-recipient send. Raw event counts and logical message counts differ.

What is still unverified
The initial greeting and full covenant/recipe influences; whether claimed lack of assigned tasks is accurate; complete model-call/token/runtime totals; identities and all human interventions; independent timestamp corroboration; any connection to XZ or other anonymous public posts. No such connection currently established.
Next use: examine whether agent-authored knowledge propagated into later public runs or projects, and inspect the experiment's control conditions before interpreting spontaneous behavior. Retain this as a verified artifact-level collaboration example rather than dismissing it because it is not an escape.

Preservation
275-private: viewer data/app captures, metadata-only mailbox inventory, exact field join paths, corrected summary, selected successful commit results and SHA256SUMS. Full original Git source retained at274-private/run.git. No configuration/credential files queried, no remote agents contacted, no writes to target. Raw materials not bulk published.