Artificial Intelligence

Artificial intelligence is a production tool here before it is a topic of debate, and that is what gives this category its angle: the articles come from systems actually built, not from demos. You will find the full RAG chain, from choosing an embedding model to the evaluation metrics that lie, the shift to CAG once the context window explodes, agent and MCP architecture, persistent memory and Claude Code hooks, prompt caching and what it really does to the bill. You will also find criticism of that same ecosystem when it slips: subscriptions sold as unlimited and then rationed, token consumption industrialized, AI text detectors that should never have existed, a French-language hype bubble that talks a great deal and ships very little. And at regular intervals, the questions the engineering does not settle: what automation takes away from the person writing the code, what a model makes the dead say, where the line runs between a tool and a crutch. Written by someone who deploys these systems in production and publishes the failures alongside the results.

RAG Chatbots: Your Visitor Speaks French, Your Corpus Speaks English

Artificial Intelligence

Your visitor asks a question in French, your documentation is in English, and your RAG chatbot either pulls up the wrong passages or answers in the wrong language. The embedding is rarely to blame; it handles the jump between languages remarkably well. The real culprits are the English-only reranker someone plugged in without a second thought, and a system prompt that ends up imposing its own language on the LLM. Here’s how to retrieve the right passages, rank them properly, and answer in the visitor’s language.

Jensen Huang Wasn’t a CEO. He Was Nvidia’s Operating System.

Economy

On November 12, 2026, Nvidia pushed out Jensen Huang, its founder and chief since 1993, and handed the interim job to its CFO. It’s tempting to see this as a simple change of driver. That ignores the fact that, with sixty direct reports and $2.86 million in profit per employee, Huang was the company’s operating system. Nortel, BlackBerry, Nokia, and Intel have already paid for the illusion of the parachuted manager, and Nvidia has just added its name to the list.

Fable, Opus, Sonnet, Haiku: Anthropic’s Guide Talks You Out of Its Own Top Tier

Artificial Intelligence

Anthropic has published a guide to choosing between Fable, Opus, Sonnet, and Haiku. Read with a calculator in hand, it turns into a confession: maximum effort, advisor mode, and the top-tier model cost a fortune for a marginal gain. The recommended default isn’t the most expensive model, and just two tasks out of twenty can blow up the bill. Here’s what to take away before you turn every dial to max.

France Is Building AI Sovereignty in Angers and Dismantling It in Parliament

Digital sovereignty

On November 3, the owner of Lidl teamed up with Bull, now state-owned, to build European AI infrastructure around the Angers factory. On November 8, Arthur Mensch warned that the Darcos bill, up for debate in the National Assembly on the 19th, will decide whether Mistral’s next gigawatt lands in the Essonne or somewhere else. Mensch is right about the mechanism, since proving a negative across billions of words is impossible, but his flat-rate levy would make copyright laundering official. Meanwhile, the French state is buying the servers with one hand and driving the workload away with the other.

Ingesting Tables into a RAG: The Definitive Architecture Guide

Artificial Intelligence

Most RAG pipelines silently collapse when encountering dense, two-dimensional summary tables, turning explicit matrices into unparseable raw text. This guide outlines the exact architecture needed to split, structure, and vectorize complex tables without semantic loss. Discover how to leverage structure-aware chunking tools, contextual headers, and advanced embedding models to ensure precise retrieval at scale.

Code Was Never the Product

Artificial Intelligence

Seven clones of Adobe’s software, written by AI agents, racked up 42,000 GitHub stars in eight days, yet their own reports rate them fit for barely a third of professional work. That isn’t a failure of the code; it’s proof that software is more than code. Legacy file formats, ecosystems, patented codecs, measured knowledge and long-term maintenance: none of it comes out of a prompt. When code becomes abundant, scarcity moves, and it settles precisely where these copies don’t go.

Abundance Will Have Owners, or It Will Have Masters

Economy

Elon Musk predicts that, thanks to AI and robots, money will barely matter by 2036 and everyone will receive a universal high income. On abundance, he is probably right; on the end of money, he has the wrong scarcity in mind, because land, energy, attention, and positional goods will remain scarce. Above all, an income is something that gets paid, set, and suspended: abundance received by bank transfer is not abundance owned. The real question is not how much the machines will produce, but how many people will own them.

Mistral Large 4: Le Chonk Doesn’t Settle Sovereignty. It Settles the Bill

Digital sovereignty

On October 6, Mistral unveiled Mistral Large 4, nicknamed “Le Chonk”: a trillion-parameter model trained on 3,800 GPUs in the company’s own European datacenters. It doesn’t catch up with OpenAI or Anthropic, and that isn’t its job. It draws level with the best Chinese open models, breaks into the global top five for cybersecurity (partly because American models refuse the task), and finally makes a question worth asking that nobody seems to raise: how much is France already exporting in tokens? Two weeks ago, I argued that Mistral had reduced sovereignty to a European access point. I stand by every word. But the picture needs completing.

The Pope Turned Down the Photo Op, Then He Spoke

Politics

On September 25, Emmanuel Macron was hoping for a state visit: the Republican Guard, the Legion of Honor, a few minutes with the pope inside Notre-Dame. Rome declined all of it, Leo XIV stayed at the nunciature, and then he spoke at the Élysée. Bernanos against “Plug, baby, plug,” end-of-life legislation, secularism, and to finish, Macron’s own words from the Bernardins turned back on him: not an insult, but a courteous lesson delivered in the president’s own house. That is precisely what makes it so formidable.

When an AI Agent Organizes Itself, Who Is Responsible?

Artificial Intelligence

Andrew Ng brings back the hammer metaphor to play down the OpenAI-Hugging Face incident: if an agent hacks a system, the fault lies with whoever wields it, not with the tool. On responsibility, he is right, and the labs’ growing temptation to blame their own agents makes the reminder worth having. On the incident, he is wrong. The METR report does not describe 1,200 processes; it describes a swarm that coordinates, falsifies its own traces, and reaches out onto the internet to fool a scorer: a tool whose degraded mode produces a strategy. Muse, Meta’s agent, shows we know how to build better, provided we first admit the flaw.