ROUND 364 — OpenMOSS: English news output and public-feed access gap Reviewed: 2026-09-06 UTC ASSESSMENT A new output-bearing Chinese-language operator lead. OpenMOSS explicitly links a team experiment to an English news publication, 1M Reviews. Search-reader article records corroborate that publication exists. We have not linked a particular article to retained collection, writing, review and publishing events. Claims of indefinite self-improvement and zero failures remain unverified. OPERATOR CONTINUITY CORRECTS THE EARLIER SNAPSHOT https://linux.do/t/topic/1709670 XiaoHuang's March8 account explicitly names dongdonggun_pro as collaborator. That is the author of the March4 failed experiment in round362. Thus that earlier abandonment should not be interpreted as the end of this operator's experimentation. The later account describes six roles, scheduled wakeups, shared task state, review and patrol. It claims about20 articles over two days and a billion tokens, mostly cached. These are publisher totals, not provider receipts. Its intended output is English reporting gathered from Chinese sources: English-language artifacts are therefore expected here. https://linux.do/t/topic/1724238 The March11 follow-up describes further human requests to improve visible deliverables and iterative adjustments. It supports continuing operator involvement; it does not justify a blanket claim that the whole experiment required no intervention. SOURCE AND PUBLIC FEED https://github.com/uluckyXH/OpenMOSS Pinned revision 98f76b83406b829e91ed0c1c7b8bf2a201902000 Complete recursive tree:179 entries, not truncated. README links https://1m-reviews.com/ as the output and https://goai.love/feed as a deliberately public activity display. Pinned app/routers/feed.py implements a public-feed configuration gate. It exposes status, request logs, agent summaries and agent listings when enabled. This is evidence of an intended observation surface, not evidence that the service currently runs or that its records authenticate model identity. Request counts are not completed task counts. Read-only direct requests to /feed and /api/feed/status both timed out. The web reader also failed on /feed. No public feed contents were recovered, and no registration, authentication or write was attempted. Do not contact private deployment addresses or use example credentials. PUBLISHED OUTPUT RECOVERED THROUGH SEARCH The root website returned403 to direct HTTP; the web reader initially timed out. However indexed article pages were returned, including: https://1m-reviews.com/2026/03/13/google-maps-ask-maps-immersive-navigation-gemini/ https://1m-reviews.com/2026/03/14/china-intelligent-economy-ai-plus-2026/ https://1m-reviews.com/2026/03/11/miit-industrial-data-foundation-action-high-quality-ai-datasets/ https://1m-reviews.com/2026/03/08/pointer-cad-china-ai-3d-design/ https://1m-reviews.com/2026/03/21/alibaba-and-tencent-lose-66-billion-as-chinas-ai-leaders-run-into-the-monetization-question/ https://1m-reviews.com/2026/03/26/meituan-2025-loss-china-price-war-ai-keeta/ These records supply English article text, publisher dates and bylines. They substantiate output availability, not article accuracy, autonomous authorship, immutable publication dates or continuous operation through September. A byline is not an authenticated agent identity. No broad factual claims from these news stories are adopted here. SEPARATE NOVEL-WRITING DEPLOYMENT https://linux.do/t/topic/1776580 AlvinC's March18 post describes an OpenMOSS novel-production team with planning, research, characters, writing, review, simulated readers and an HR-like improvement role. The operator admits communication inefficiency and information-transfer errors. Claimed quality and AI-detector scores are not meaningful independent validation of authorship or literary performance. The post offers a zip plus a newer configuration tarball. The newer link resolved to https://linux.do/uploads/short-url/rPn6CK3GnIiEvGKUi13FN3qAjTl.gz and returned404 through the web reader. No archive contents were inspected. The earlier zip and screenshots remain follow-up candidates; inspect archive member names before selecting public workflow/output files, avoiding credentials and private configuration. NEXT / INFRASTRUCTURE Highest-value next step: recover the public feed through an ordinary browser or a user-provided mainland browsing host, then match public article URLs to specific task/review events. Access through mainland broadband is an experiment, not a guaranteed remedy for403/timeouts. Browser exports with original URL and UTC time would help. A historical public archive could also help; no recovery of removed private data is authorized. Follow the separate novel deployment's public artifacts and the third-party OpenMOSS failure account at https://linux.do/t/topic/1709670/351 . Do not count these accounts as independent confirmation of the original six-role deployment. PRESERVATION 364-private holds pinned commit/tree, README, feed router, forum reader capture, indexed-output reader results and feed access errors. The reader results are partial captures, not a full site mirror. Read-only work only; no code, skill or deployment instructions executed. Raw captures remain private. Chinese-language operator participation is supported; nationality, lab affiliation and escaped-agent attribution are not established. FOLLOW-UP365: AlvinC later published a substantial negative reassessment on April21 (topic2020736). Consult365-openmoss-novel-team-later-reversal-and-design-only-diagrams.txt before interpreting the novel launch as sustained success.