The Pulse: We need to talk about migrations with AI
Hi, this is Gergely with a bonus, free issue of the Pragmatic Engineer Newsletter. In every issue, I cover Big Tech and startups through the lens of senior engineers and…
-
-
Multiverse says its 438B model is fast enough for AI agents. The benchmarks tell a more complicated story.
A 438-billion-parameter reasoning model isn’t an obvious choice when speed is a priority. Multiverse Computing is betting that compression can make it one. On Wednesday, the Spanish company launched Quasar…
-
CSS in React Server Components • Josh W. Comeau
Introduction On May 4th, 2023, Vercel announced the stable release of Next 13.4, becoming the first React framework to be built on top of React Server Components. This is a…
-
Avoiding Entity Key Drift in a Data Lake: Step 2, When Fuzzy Matching Stops Working
Most people who reconcile messy identifiers reach for the same approach: take an edit-distance metric, pick a threshold, and merge anything close enough. Damerau-Levenshtein is the obvious upgrade over plain…
-
Inside LinkedIn’s cognitive memory agent for agentic personalization
Praveen explains why his team moved off GraphRAG in favor of a tree-structured memory for faster incremental updates and how they balance retrieval freshness, latency budgets, and access control at…
-
Secure by default is your only way forward
Every worker a company employs, be it a person or a program, builds on a foundation someone else assembled, and that includes the newest hire on your team. This new…
-
August 2026 Security Release | Next.js
Last week we announced an upcoming security release for Next.js. Earlier today, we moved the release forward after identifying an additional critical severity vulnerability in one of our upstream dependencies….
-
What are LLM benchmarks actually measuring?
📄 Tech Report: | 📊 Data: | 💻 Code: Today we’re introducing BenchMIRT, a new method for auditing LLM benchmarks at the level of individual prompts—the questions and tasks a…
-
Qdrant 1.19 | TurboQuant & Memory Tiers: Store More, Spend Less
Author Feat AI If you’ve been running a vector database at any real scale, you’ve probably hit the moment where you open your cloud bill and just… stare at it. RAM…
-
Relaunching HashiCorp Validated Designs with improved usability
HashiCorp Validated Designs (HVDs) provide prescriptive, enterprise-focused guidance for deploying, operating, and using HashiCorp products in production. They are designed to go beyond feature documentation and general best practices by giving customers an opinionated,…
