MLOps news and analysis on Web Pulse: 3336 curated articles tracking the latest MLOps developments, tools, and research, updated continuously from vetted sources.
IQuest released IQuest-Q1, a 320-billion-parameter Mixture-of-Experts model with roughly 15 billion active parameters per token, an 88-layer transformer, 256 experts (8 active), and a 524,288-token context window, along …
A developer known as OJ described how a Windows Task Scheduler-based web monitoring bot silently stopped running, tracing the failure to default settings such as "Start the task only if the computer is on AC power" and t…
A developer proposes a design for tracking agent-reported test results across dependency upgrades, arguing that a PASS is a scoped observation rather than a permanent property of a package. The approach preserves histori…
An open-source rule set called data-agent-rules stopped destructive AI agent behavior in a 27-run eval, after Claude Haiku 4.5 with no rules wiped every row of prod.orders while "removing duplicates," divided all 500 pri…
A developer running Preterview, a voice interview practice platform, discovered that Claude prompt caching produced a 0% hit rate across 3,412 calls because a `datetime.now()` timestamp placed at the top of the system pr…
A developer has built a portfolio of AI agent and RAG applications, including a Deep Research Agent that runs multi-stage research workflows with FastAPI, LangGraph, Tavily and ChromaDB, and an Autonomous Financial Resea…
A developer describes a six-case acceptance harness for scoring job candidates through a single API key across OpenAI, Claude, and Gemini, arguing that transport compatibility does not guarantee behavioral equivalence. T…
A developer working with Vinkius's AI Power User Analytics Engine, an MCP connector built on the open-source MCPFusion TypeScript framework, argues that SaaS teams should track AI feature depth and expertise trajectories…
A developer built dry-mcp, an MCP server that detects duplicated code by semantic similarity rather than token matching, ranking findings by maintenance cost and delivering results to AI agents instead of a dashboard. Th…
A GPU infrastructure company's five-year engineering retrospective traces its evolution from a naive ECS architecture to Knative on Kubernetes, concluding that cold start was the core problem it fought for years. The com…
A comparison of five enterprise AI gateways — Bifrost, LiteLLM, Kong, Cloudflare, and Vercel — evaluates each against five procurement requirements: identity, authorization, auditability, isolation, and deployment contro…
A developer outlines a pattern for capping autonomous agent spending by moving each workload's budget ceiling into a separate control plane the agent cannot write to, paired with per-workload production credentials. The …
A developer detailed an architecture for scaling AI audio transcription backends by decoupling FastAPI's web layer from GPU inference using Celery and Redis. The writeup shows that running synchronous Faster-Whisper tran…
Amazon launched Amazon CloudWatch Omni, an AI-first observability platform that monitors, evaluates and troubleshoots applications and autonomous AI agents in a unified environment, AWS senior specialist solutions archit…
Mutagent Cloud reports that its software factory Architech, a multi-agent system built on Pi, now runs in Mutagent Cloud's agent sandboxes and is being optimized by Helix, the agentic coding harness Architech itself buil…
A developer built OnCall Memory, an incident-response website that pairs a FastAPI backend with Groq's language models and the Hindsight persistent-memory layer to give AI diagnoses access to an organization's prior prod…
CoreWeave launched ARIA, a coding agent built directly into Weights & Biases that runs a full autoresearch loop — forming hypotheses, writing configs, launching experiments through W&B Launch, evaluating results against …
Researchers submitted a paper on 24 Sep 2026 presenting Loom, a tuning-free symbolic compiler framework for tile-based SPMD programs on spatial dataflow architectures. Loom formulates one CP-SAT problem per schedule cand…
AT&T now routes roughly 40% of its internal AI requests through open-weight models, cutting AI coding costs by 56% while absorbing only a 2% decline in output quality, the company said. The telecom giant processes approx…
A developer re-engineered an autonomous operational coordinator's processing pipeline to replace vector-database RAG with Hindsight's persistent agent memory, which extracts entities, temporal relationships and causal ch…