All posts

• macfleet-dash v0.10.0: AI engines join the fleet view
  Oct 29, 2026 — The October 20 release brings optional SparkDash engine cards, token windows and resource history into macfleet-dash. What the released code adds, and how to read it.
• What I would test with a third 128 GB DGX Spark
  Oct 29, 2026 — A practical research plan: keep an existing Spark pair available, isolate experiments on a third system, and compare a three-node cluster with a pair plus a worker.
• Two AI agents can undo each other’s fixes. The race was in a file write.
  Oct 17, 2026 — A recovery helper replaced a genuine resolution record. What the incident and a temporary-state race test taught me about check-then-write, exclusive file creation and the limits of a passing regression.
• My AI setup: what runs locally, what goes to the cloud, and what actually does the work
  Oct 17, 2026 — Hermes is the working environment, not the model. How I separate a two-DGX local route, cloud inference, bounded tools and a fleet dashboard—and how an actual article moves through that setup.
• Your dashboard says a model is running. Is it really?
  Oct 17, 2026 — A saved role, an old benchmark and a fresh endpoint report answer different questions. What macfleet-dash v0.9.4 checks, what it leaves unverified, and how I read the result without overstating it.
• What daily Hermes use actually looks like: the updater that interrupted the work
  Oct 15, 2026 — An October 13–14 operator log, updated October 17: interrupted jobs, unsafe green tests, and a wider claimed/running execution barrier—with separate regression, installed-probe and natural-skip evidence.
• My Mac fleet dashboard learned Windows. The hard part was knowing what not to count.
  Oct 15, 2026 — What the October 14 macfleet-dash releases actually added: private Windows telemetry, honest pilot states, per-drive warnings, and a clear boundary between released code and unattended monitoring.
• Content at scale: what the publication numbers actually prove
  Oct 13, 2026 — A content publishing case study: dated evidence of scale, an unresolved inventory mismatch, and why neither volume nor a passing audit establishes business return.
• Search visibility: separating accepted URLs from indexed pages
  Oct 13, 2026 — A search reporting case study: 1,839 indexed URLs and 4,879 IndexNow acceptances in dated assessments, without treating different cohorts as a conversion funnel or proof of sales.
• Deals email: why an attempted send is not a delivery result
  Oct 13, 2026 — A Rapid Fire Deals case study in reporting a failed send honestly, keeping activity separate from delivery, and refusing to turn incomplete evidence into a success rate.
• Retiring a model the right way: the Qwen decommission checklist
  Oct 13, 2026 — Six cron jobs, four dead providers, a dispatcher path, and a pile of presets — the ordered checklist for removing a model from a live fleet with checked client paths and an explicit host-verification gap.
• The Spark pair: serving one local model on two NVIDIA DGX Sparks
  Oct 13, 2026 — One local-model route across two desk-side DGX Sparks: dated serving measurements, memory failures and repairs, and the limits of GPU-only telemetry.
• No invented numbers: the flag system behind this site
  Oct 12, 2026 — How this blog decides what gets published: three flags for unproven claims, a status field that does not certify truth, and a house rule that every number carries a receipt.
• Week one in public: shipping a static site on Cloudflare Workers
  Oct 12, 2026 — The actual build log for this site: an Astro scaffold, a static-assets Worker, one deploy command, the custom-domain cutover — and the receipts for each step.