- · local-llm · gpu
Tuning vLLM on a Modded 48GB RTX 4090: From 18 to 133 Tokens per Second
Three days of benchmarking vLLM on a modded 48GB RTX 4090: the quantisation trap that costs Ada owners 40% of their speed, the free 1.9x from speculative decoding, the KV compression that never served once, and what cutting 120 watts costs you. Every number measured, every failure kept.
Read article - · claude-code · mcp
Giving Claude a Local Sidekick: a vLLM Journey Update
I want Claude to have a powerful local sidekick through houtini-lm. I'm not there yet, but this month I got noticeably closer - a vLLM rebuild, a benching spree on the 48GB 4090, and a face-off that deleted two models in an evening.
Read article - · strategy · claude-code
AI for the CFO: variable cost, vendor sprawl, and the playbook that ends the surprise bill
Uber reportedly provisioned 5,000 engineers with Claude Code in December 2025. By April 2026 it had burned the entire annual AI budget in four months. Variable cost is the new shape of the AI line item, and the CFOs who are getting it under control are running the same four-lever playbook. Here is what is on each lever, which platforms are credible, and what to ship in the next ninety days.
Read article - · Claude · strategy
AI hallucination, and the boring discipline that stops it being a problem
You have read about lawyers citing made-up cases and chatbots inventing refund policies. The fix is not a new platform or a clever prompt. It is the most boring discipline in software: read what came out and check the bits that matter against a second source. Here is what hallucination is, how we run a Houtini-grade check on every claim, and what would change if your team did the same.
Read article - · Claude · strategy
What is RAG, and what could it do in your company?
Your AI confidently answers questions about your business with public-internet knowledge. RAG is the architecture that gets your actual contracts, customer list and operating playbook into the conversation, with citations. Here is what it is, where it sits next to long context and MCP, and what it changes if you sponsor the work this quarter.
Read article -
The Bitcoin Spiral: How I Built a Live AI-Narrated Dashboard on GitHub Pages
I spent an afternoon building a live Bitcoin dashboard on GitHub Pages with no backend, no paid API key, and a frontier model writing the verdict at the top of the page every six hours. Here's how it works, what it cost (nothing), how to stop the model inventing numbers, and where the architecture goes next when Chrome ships in-browser inference.
Read article -
What Are AI Agents? The Plain-English Explanation
An early-user's view of AI agents. Where they fit relative to chat and MCPs, what counts as agentic, and the simplest first agent to build inside Claude Code.
Read article