2d ago · 18 min read · 🗓️ Last updated June 2026. Field names and stability levels track the still evolving OpenTelemetry GenAI semantic conventions; check them against the official spec on GitHub before adoption. There's
LMLara and 3 more commented
3d ago · 8 min read · I have a document assistant that answers questions from enterprise cloud documentation. Azure OpenAI generates the answers, Azure AI Search handles retrieval. It works. People use it. The answers soun
Join discussion
May 6 · 10 min read · Last week was loud for AI. Five separate stories ran the front page of every tech outlet, every newsletter, every Slack channel that takes itself seriously. Anthropic admitted three quality regressions its own evaluation suite missed. GitHub announce...
Join discussion
Apr 22 · 4 min read · The Arabic LLM Gap Nobody's Measuring Most benchmarks tell you how well a model speaks English. QIMMA asks a harder question: does it actually understand Arabic? Not the textbook version. The real thing—poetry, dialects, classical grammar, modern sla...
Join discussionApr 17 · 20 min read · TLDR: Most bad LLM products do not fail because the model is weak. They fail because teams wrap a maybe-useful model in too much architecture: prompt spaghetti, no eval harness, weak tool schemas, hug
Join discussion
Apr 13 · 16 min read · Your engineer walks into the ship review with a slide. The slide has one big number on it: "87%." Below the number, in smaller text: "eval set pass rate, up from 82% last week." The room nods. Someone says "great work." The PM is about to say "OK shi...
Join discussion
Apr 13 · 18 min read · You have an eval set. You know your rubric. You want a pass rate. Now a new question appears: who decides whether each individual output is a pass? You, reading them one by one? A rule engine that checks for specific strings? Another model that grade...
Join discussion
