A search service (Marginalia Search) gutted its old index internals and dropped memory-mapped B-trees. In their place: adeterministic, block-aligned skip listtuned fordirect reads on NVMe SSDs. It runs on128KB block sizes, usescustom buffer pools, and leans hard onio_uringfor async position lookups..

GitHub just lost its autonomy. Microsoft is folding it into theCoreAIdivision, where it’ll now march in step with Redmond’s broader AI play. CEO Thomas Dohmke is out. No replacement named. Bigger picture:Why now? Copilot hit general availability, and GitHub’s becoming less a platform, more a provin..

An indie dev just went full mad scientist and built a full-stack, transformer-powered search engine—solo. They indexed 280 million pages from scratch with hundreds of crawlers, a fully sharded backend, and serious metal:64 RocksDB nodes,200 CPU cores, and82 TB of SSD. Under the hood: custom HTML pa..

Node.js just got spicier. You can now runTypeScript files out of the box—no transpile step, no weird configs. It’s experimental, and only supports a trimmed-down syntax, but still: big move. Elsewhere, it’s tacklingburst fs eventswith AsyncIterator support, tightening upCJS/ESM cycle resolution, an..

Claims of 10–100x dev speed from AI tools skip the hard parts—code reviews, bug queues, flaky tests. In practice, AI helps with the small stuff: one-off scripts, throwaway glue code, basic scaffolds. But scaling that help across big, messy codebases? Still a pipe dream. Too much context lost. Too ma..

A new LLM evaluation framework taps into an"LLM-as-judge"setup—think strong model playing human annotator. It gets prompted (or fine-tuned) to mimic human scores and rate outputs from other LLMs. It runs on a tightly labeledgolden dataset, handles both pointwise and head-to-head comparisons, and sh..

A fresh dive into 24,910 top Hacker News posts since 2019 shows that AI chatter didn’t blow up with ChatGPT—it took off afterGPT-4 landed in early 2023. The study used OpenAI’s Batch API and a lean GPT-5-mini to crunch the numbers. Turns out,52% of the AI talk was positive, and the busiest stretch?..

Gradio just leveled up. It now auto-converts plain Python functions intoMCP-compliant LLM tools, grabbing input schemas and metadata straight from docstrings. New tricks:real-time progress streaming,auto file uploads, plus tight integration withVS Code’s AI Chatfor wiring up agent workflows...

Azure just droppedMCP Center, showing off howAzure API Centercan double as a private registry forModel-Centric Protocol (MCP) servers. It’s built for internal use—think secure discovery, tight OAuth 2 auth, centralized control, and AI Gateway rules baked in. Handy when teams need to corral AI tools..

Microsoft just leveled upNLWeb. The open-source project now plays nice withPostgreSQLandpgvector, bringing scalable vector similarity search straight into your database. No need for a separate vector DB—run natural language interfaces right on your existing Postgres stack. System shift:This is more..