LingTai forty-agent claim and Nira public runtime metadata
Reviewed September 6, 2026 UTC

Forty-agent source trail
https://www.xinfinite.net/t/topic/19854
This readable secondary copy contains a forty-agent social-behavior claim and promotes a May31,21:00 discussion involving Li Bojie and Huang Shuzhi. It links a WeChat original (captured URL in local secondary HTML). That original returns an environment verification challenge here despite HTTP200. A CSDN copy returned404. Another indexed announcement, https://www.10100.com/article/146899798, returned403 directly. No replay or forty-agent dataset recovered. The promotional claim must not be counted as a second verified experiment or conflated with the twenty-agent dataset in reports274–276.

Author context from primary website
https://lingtai.ai/zh/about/ identifies Huang Zesen and Shuzhi as the same author and describes Guangzhou origins; https://lingtai.ai/en/about/ describes the author's UCLA research background. These are self-descriptions, not independently verified biography. They strengthen the Chinese developer context while providing no Chinese AI-lab attribution.

New linked public surface: Nira
https://lingtai.ai/en/projects/ links https://nira.social/worldcup2026 as a LingTai-style project. Page GET200. The bilingual page describes a thirty-role system: five lead roles and twenty-five reviewer roles. A frontend asset contains a literal five-subagents-validating label; the label itself is not a live process probe.
The page's own frontend reads this public GET endpoint:
https://nira.social/api/worldcup2026/latest-site-data
Inspected only that read route; no protected run/evolution endpoint invoked.

Observed metadata contradicts an easy live-agent interpretation
Public JSON GET200,602191bytes. dataSource=runtime; sourceType=runtime_store_snapshot. isStale=true, staleReason=snapshot_stale. generatedAt and sourceFetchedAt are2026-09-06T01:02:31.155Z.
runStatus reports lastRunStatus=success, lastRunTrigger=manual, idempotentNoop=true, completedDetected=94, evaluatedDetected=94, fallbackCount=94, agentAuthoredCount=0.
latestSiteData.canClaimOriginalPreMatchAccuracy=false.
These are site-reported fields, not independently authenticated execution records. They provide no support for describing the latest snapshot as94 agent-authored forecasts or thirty currently running agents. They also do not prove that agents were never used historically.

What the payload contains
worldState has104 predictions,255 modelEvolutionEntries and two agentDebates. One inspected debate entry contains role names, summary text and adjustment metadata, not individual speaker messages or model tool calls. A sampled evolution entry includes a rule-version label and result-source provenance. The page's performance and simulated-bankroll displays have not been independently validated and are not financial guidance. No need to verify match scores to establish this agent-evidence limitation.

Interpretation / next actions
Nira is a useful public-output lead with unusually candid status metadata, but currently weaker than LingTai's actual mailbox export. Follow provenance and public source links if further inspection can join an agent-authored artifact to a run; do not infer model invocations from role animations, summary strings or a success flag. The forty-agent story needs its original recording or published data.

Infrastructure
The exact WeChat challenge is a useful comparison target for an owned mainland browser. HTTP200 does not mean the article was retrieved. A different server may not solve browser/session verification. Nira's page, source asset and public data route work from this server; no additional infrastructure needed for those.

Preservation
277-private stores secondary/blocked-page captures, author pages, Nira homepage, identified frontend asset and public latest JSON. SHA256SUMS covers captures. Whitelisted metadata only mirrored publicly; no raw payload or contact details republished. No messages, accounts, subscriptions, simulations, wagers or protected actions performed.