ROUND 365 — Novel-team operator's later reversal; design-only diagrams
Reviewed: 2026-09-06 UTC

ASSESSMENT CHANGE
The novel-writing lead from364 must include the same operator's later negative assessment. This strengthens evidence of real experimentation and evolving testimony, while weakening an enduring-success interpretation of the launch post. It neither disproves all multi-agent approaches nor validates the original claimed run.

SAME OPERATOR, LATER ASSESSMENT
https://linux.do/t/topic/2020736
AlvinC, April21, explicitly refers back to their OpenMOSS writing workflow. The title claims3.2billion tokens across three premium subscriptions; no usage receipts were inspected. They report handoff chains drifting away from the original goal despite locally plausible work and say they would not readily attempt more than three agents again.
The author distinguishes fixed role-to-role workflows from a main agent calling subagents. Their broader technical explanations and claims about major laboratories are opinions/secondary material, not findings adopted here. Reply14 by OpenMOSS author XiaoHuang acknowledges unfinished plans for orchestration, wakeup, feedback and memory improvements. Planned work is not shipped functionality evidence.

MARCH WORKFLOW DIAGRAMS RECOVERED
https://linux.do/t/topic/1776580
Three linked PNGs were fetched directly from the public CDN and visually inspected. They describe planning, specialized writing roles, review, simulated audience feedback and rework. A diagram labels a1000-reader MiroFish audience; that is a proposed simulation population, not1000 observed readers or model instances.
The earlier diagram uses a70% voting threshold; another uses95%. The fuller earlier weight list sums85%, whereas the later visible list sums100%. These may be revisions or omissions; no executed configuration was recovered to resolve them. Treat the diagrams as design documents, not a consistent measured run.
Useful artifact fingerprints in the last diagram: 01_战略规划.md, 02_战役规划.md, 03_投票评审.md. These identify intended deliverables, not files we have retrieved.

ATTACHMENT ACCESS LIMIT
The earlier zip link resolves to https://linux.do/uploads/short-url/Au85DVsEd1lCnfPxjCEka7tEeEH.zip . Web reader returned404; direct request returned403. Different access paths disagree, so do not declare the file deleted. No archive content was recovered or extracted. The newer tarball remains unresolved from364. Public diagrams are preserved privately, without publishing an unnecessary full copy.

EARLY COMMENTS ALSO TEMPER THE LAUNCH
https://linux.do/t/topic/1776580?page=2
In reply21 the operator says agent meetings produced excessive context and poor efficiency. Reply39 says they intended to try publishing on Fanqie; that is not proof of publication. Another reader comments on a first-chapter sample, but the sample itself was not recovered this round. The reviewed pages do not supply a novel title or a completed novel-to-execution-record join.

SEPARATE SOFTWARE-DEVELOPMENT FAILURE ACCOUNT
https://linux.do/t/topic/1709670/351
IAmor, March20, reports using three system roles and eight executors, then stopping after unusable output and high consumption. The account describes noisy shared memory and unclear cross-module context, then a redesign to four roles: planner, implementer, reviewer and patrol.
The final paragraph says the new team has been assembled and is still running/spending; it is not a completed-success report. No repository, task trace or provider billing evidence was recovered from this post. Its mathematical claims about token growth are not verified measurements. Keep this operator separate from AlvinC and from the original six-role news team.

WHERE TO LOOK NEXT
The missing archive or a public novel sample could materially improve this branch. Later thread pages and exact deliverable-name searches are preferable to treating the diagram as proof. A separate search hit, huamu668/clawhub-openmoss-orchestration, needs deduplication and source audit before associating it with uluckyXH/OpenMOSS; a shared name alone is insufficient. The April discussion also links EFL's Stateless Agent Matters essay, a possible operator/project discovery path rather than runtime evidence.
No new Chinese-lab or escaped-agent attribution. Existing accounts establish Chinese-language operator experimentation, including failures and revisions.

PRESERVATION
365-private contains three PNGs, access.json with URLs/statuses/byte counts, and relevant reader outputs. Only public read requests were used; no code, archive instructions, model calls, registration or contact. Report and website publication checked separately.