An LLM gateway is a small system with a big trust load. It's small enough for one on-call to own, and it holds your org's model credentials, its spend attribution and its audit trail. That combination shapes how you run it: conservative where the trust is, pragmatic everywhere else. The runbook set…
On September 8, 2026, Inception Labs announced Mercury 2.5 — which the company describes as the largest diffusion language model ever trained. The headline number: 1,107 tokens per second on widely available NVIDIA GPUs, at quality the company says matches the cost-optimized frontier tier (GPT-5.6…
Free API tiers get farmed. That is not news. What surprised me was how much the farming looked like real evaluation, and how badly a model did at telling the two apart. This is a Companydata story: Danish company registry data over HTTP, a free monthly quota, and a tripwire that throttles keys that…
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass What I Built I built a small paper trading system for a friend who is interested in financial markets and wanted a way to experiment with trading ideas without putting real money at risk. The idea was to combine…
Following one question through the MCP stack — from the user's prompt to the final answer Modern AI applications increasingly sit between two different worlds: MCP (Model Context Protocol) and an LLM provider API . MCP provides a standardized way for an AI application to discover and invoke…
Streaming is table stakes for an AI app now. People expect the answer to appear word by word, not after a 20-second spinner. Here's the setup I use in Next.js 15 with the Vercel AI SDK, plus the two things that quietly trip people up. The route handler // app/api/chat/route.ts import { openai }…
A language model can make a game character say almost anything, which is the easy part. The hard part shows up the second time a player walks up to that character, and the NPC greets them like a stranger. Memory is what separates a tech demo from a character players care about. Here is a practical…
Every few weeks new open-weight model is released with a table of benchmark results, and every few weeks we asked the same practical question: is it better than the one we already run? A single ranked list should answer that. Building one turned out to be harder than we expected, and our first…
