Find articles, news, tools and templates by subject or by the work you need to do.
83 results for “Improve a postmortem” · 25–36
News · Platform engineering ·
Maia 300 joins chiplets, memory locality, networking, software, power and cooling. The operational test is accepted work under the same demand.
Read news: Microsoft Maia 300 makes inference efficiency a systems problemNews · Platform engineering ·
The October 12 OCP release spans rack designs, facility specifications, open-source operations software and planned optics. Operators should test each layer against workload evidence.
Read news: NVIDIA opens more of the Vera Rubin infrastructure stackExplainer · AI in production ·
Compare reference and speculative paths for token-level equivalence, then run a separate capacity trial so speed cannot conceal a serving-contract change.
Read explainer: Bit-exact decoding turns inference speedups into testable changesExplainer · AI in production ·
Measure cached input against total input, locate the prefix miss boundary, and judge cache changes beside latency, task cost and correction work.
Read explainer: Long agent sessions need a prompt-cache SLIExplainer · Platform engineering ·
Basalt narrows local inference to Qwen3.8-Flash-Next on Blackwell. Its memory and concurrency controls matter more than copying the largest throughput number.
Read explainer: What Basalt changes in a Blackwell local inference stackGuide · Observability ·
Run a candidate log classifier beside the current route, preserve complete outcomes, and promote only the slices whose mistakes and review cost are understood.
Read guide: Shadow-testing an AI log classifier before migrationNews · AI in production ·
Claude Haiku 5.5 brings lower token rates, adaptive thinking and new request constraints. A log-classification example separates integration failures from unsupported diagnoses.
Read news: Haiku 5.5 lowers prices and changes what a log classifier must handleExplainer · AI in production ·
Anthropic’s October 7 credits add a Console-funded path for eligible subscribers. Subscription access remains, while scheduled agents still need task budgets spanning retries and verification.
Read explainer: Claude’s new API credits do not remove Agent SDK subscription accessGuide · Observability ·
A client-side SSE probe separates first answer text from normal completion. Fixed arrivals and outcome counts show whether a serving change delivers more useful answers.
Read guide: Measuring streaming LLM latency from first text to completed workGuide · AI in production ·
Instinct brings personal tasks into connected services. A hypothetical booking and notification worker show how permission, provider confirmation and uncertain results affect what happens next.
Read guide: Instinct: from a text or call to a confirmed taskNews · AI in production ·
Google's new image model rejects familiar generation settings. Follow a thumbnail job through its outgoing request, retries and delivery to evaluate the upgrade.
Read news: What Nano Banana 2.1 changes in an image-generation serviceNews · AI in production ·
Wikimedia’s October 5 disclosure covers unapproved edits, proxy attempts and heavy downloading. Activity windows remain unresolved; the linked WDQS outage was in May.
Read news: Wikimedia reports unapproved activity by suspected OpenAI agents