Search stories, models, companies…
Subscribe

Popular topics

OpenAI83Anthropic81Google Gemini45Claude Code27Coding agents51Model Context Protocol (MCP)13
The week in AI, in one email.
The river

Latest

Every story as it’s published, newest first.

Friday, Oct 9

19 stories
Models · ExplainerHow to choose a small AI model for your laptop: the memory math and the current shortlistParameters, quantization and context length decide whether a model fits. Here's how to do the arithmetic, and which open models to try at 8, 16 and 32 GB.·7 min readAgents · ExplainerOpenAI Codex explained: where it runs, which models and limits you get, and how its sandbox worksWhat Codex is in October 2026, from OpenAI's docs and pricing pages: where it runs, which plans get which models, how far the allowance goes, and what its sandbox enforces.·7 min readAgents · ExplainerClaude Code mods, explained: what Anthropic's new extension layer can do, where it runs, and the security trade-offSince October 1, 2026, Claude Code can load JavaScript and TypeScript 'mods' that redraw its interface, rewrite prompts and approve tool calls. What Anthropic's docs say they can do, and what they can reach.·8 min readPolicy · ExplainerWhat the EU AI Act means if you only use model APIsYou may never train a model and still be a "provider" under the AI Act. How the roles work, which duties are live in October 2026, and a checklist for teams building on hosted models.·8 min readDevelopers · ExplainerModel routing explained: how to mix cheap, mid and frontier modelsSending every request to a frontier model can cost 40 times more than it needs to. How routers, cascades and advisor patterns work, and what vendors actually offer.·8 min readModels · ExplainerReasoning models explained: thinking tokens, what they cost, and when to use themClaude, GPT-6 and Gemini all bill hidden thinking as output tokens. How each vendor exposes it, what it costs in practice, and when to turn it down.·7 min readModels · GuideWhich Claude model should you use? The current lineup and official pricesOpus 5.5 is Anthropic's default pick, Haiku 5.5 (October 7, 2026) is far cheaper than Haiku 4.5, and Fable 5.1 is for the hardest jobs. The verified lineup, every price, and how to choose.·9 min readDevelopers · GuideBuild your first agent with the Claude Agent SDK (TypeScript, October 2026)Install @anthropic-ai/claude-agent-sdk, call query(), lock down tools and permission modes, add a custom MCP tool and a safety hook, and cap spend. Code type-checked against v0.3.293.·7 min readDevelopers · GuideHow to write a CLAUDE.md or AGENTS.md file that coding agents actually followWhere each agent looks for its instructions, how long the file should be, what to put in it, and how to check the agent is reading it, from Claude Code, Codex, Cursor and Copilot docs.·10 min readOpen source · GuideHow to run an open model locally with Ollama (October 2026)Install Ollama, pull a model, chat with it, call it from code, and keep the server off the public internet. Every command comes from Ollama's official documentation.·8 min readIndustry · ExplainerOpenAI explained: who controls it, what it sells, and how it makes moneyFrom a 2015 nonprofit to a public benefit corporation reportedly seeking a $1.4 trillion valuation: OpenAI's structure, Microsoft deal, products, prices and revenue.·7 min readIndustry · ExplainerAnthropic explained: history, products and how it makes moneyFounded in 2021 by former OpenAI staff, Anthropic was valued at $965 billion in May 2026. Here's how it's governed, funded and paid, and what's unresolved.·9 min readPolicy · ExplainerThe EU AI Act in October 2026: what actually applies nowThe AI Omnibus pushed high-risk rules to late 2027, but general-purpose AI obligations, transparency duties and EU enforcement are already live. The dates, from official EU sources.·9 min readResearch · ExplainerHow to read a system card: a builder's guide to AI safety documentationSystem cards run to hundreds of pages. What the sections mean, which safety frameworks they report against, how to read eval tables critically, and a checklist.·7 min readResearch · ExplainerContext windows vs memory vs RAG: what each one actually doesA 1M-token window, a chatbot that "remembers you" and a retrieval pipeline solve different problems. Here's how each works and when to use which.·7 min readDevelopers · ExplainerMCP resources vs tools vs prompts: who decides, and when to use eachMCP servers expose three primitives with three different owners: the model, the app and the user. Here's how each works on the wire in the 2026-07-28 spec, plus what happened to sampling, roots and elicitation.·6 min readDevelopers · GuideBuild a local MCP server with the official TypeScript SDK (v2): one tool, one resource, one promptA step-by-step guide to a stdio MCP server using @modelcontextprotocol/server 2.3.1, with code we compiled and ran to check it works, plus the MCP Inspector, Claude Desktop and Claude Code.·5 min readAgents · ExplainerWhat "agentic" really means in 2026Every AI product now calls itself agentic. Here's the definition the labs themselves use, how the tool loop works, and how to tell a real agent from a relabeled chatbot.·6 min readAgents · ExplainerWhat is MCP? The Model Context Protocol explained (2026 edition)MCP is the open standard that lets AI apps plug into tools and data. Here's how it works, who governs it, what changed in the stateless 2026-07-28 spec, and where the risks are.·9 min read