AI Infrastructure news and analysis on Web Pulse: 28215 curated articles tracking the latest AI Infrastructure developments, tools, and research, updated continuously from vetted sources.
A developer introduced the Cowork Loop, a four-phase software pattern for AI workflows that includes a critical Refine phase often skipped. The pattern emphasizes updating shared context after each session to compound im…
Echelon Graph released real-time metrics for exposed databases, leaked credentials, exposed AI keys, KEV exposures, and subdomain takeovers, based on continuous scanning. The data is available at dedicated URLs for each …
A company running a self-hosted AI business platform since early 2026 shares seven painful lessons from building production RAG systems, including the need for document-type-aware chunking and hybrid retrieval combining …
Model routing, which directs simple tasks to cheap models and complex ones to frontier models, can cut AI costs by 40-70% in 2026 while mitigating vendor dependency risks highlighted by Fable 5's suspension and GPT-5.6's…
Mem0, an open-source memory layer for AI agents with nearly 60,000 GitHub stars, has released v3.0 with temporal reasoning and multi-tenant isolation. The project scored 94.8 on LongMemEval and 91.6 on LoCoMo, proving me…
Vale inaugurated its first AI-powered Model Plant at the Conceição 2 unit in Itabira, Minas Gerais, on June 10, with an annual capacity of 11.2 million tonnes. The plant achieved a 25% productivity gain and 40% increase …
SandbaseAI maintains Awesome Agent Runtime, a curated map of 500 projects across the production AI agent infrastructure stack. The project argues that as agent conversations shift from one-shot prompts to repeated loops,…
A developer built a multi-provider AI routing layer after a junior engineer accidentally caused a $3,200 monthly bill by leaving a loop running in production. The solution uses a configurable Python class that selects pr…
Governor-elect of North Jeolla Province Lee Won-taeg invited Nvidia CEO Jensen Huang to a casual K-BBQ dinner in Saemangeum, proposing the reclaimed land as a hub for Nvidia's AI technology. Lee touted Saemangeum's clean…
A developer building agentic workflows with LLMs like Claude or Cursor found that standard HTTP requests fail to retrieve data from modern single-page applications because the content is rendered client-side. To solve th…
Khronos Group presented an open standards roadmap at SIGGRAPH ASIA 2025 in Hong Kong, December 15-18, covering cross-platform ML inferencing acceleration, glTF Gaussian Splats, and OpenXR Spatial Entities. The Machine Le…
Developer alih552 released mcp-audit, a zero-dependency CLI tool that scans MCP server configurations for security issues, after a 2026 analysis of ~7,000 public MCP servers found 41% require no authentication and 36.7% …
Hong Kong is investing billions of dollars in AI projects, including a semiconductor centre, an AI subsidy scheme, and a data centre, but critics argue the city needs a broader vision and more realistic goals, as it cann…
ProjectDiscovery Nuclei, an open-source vulnerability scanner, suffered from memory and goroutine leaks when embedded in long-running applications. A developer identified three primary leaks: an unbounded sync.Map in the…
Ollama provides a tool for running large language models locally on macOS, Linux, and Windows without requiring an API key or cloud service. The tool packages model weights, a runtime based on llama.cpp, and a CLI/REST A…
A developer built a real-time AI recommendation agent using AWS Bedrock, Kinesis, DynamoDB, and S3. The system reacts to streaming user behavior within seconds, updating recommendation sets asynchronously without blockin…
OpenAI launched GPT-5.6 on June 26 with three tiers: Sol, Terra, and Luna. Luna, the economy tier at $1 per million input tokens, is designed for high-volume tasks like summarization and classification, offering signific…
A developer argues that AI agents will not replace humans in production engineering because they lack the ability to understand context, own consequences, and take responsibility. The post warns that giving AI agents unl…
Moumantai, a self-hosted runtime for creating personal mini-apps, was released on Hacker News. The platform allows users to define apps once with schema, tools, and faces, then access them natively across devices via a t…
AMD Strix Halo cluster setup guide details how to configure a two-node system linked via Intel E810 RoCE v2 for distributed vLLM inference using Tensor Parallelism. The guide covers hardware prerequisites, host configura…