A silent failure mode that almost nobody talks about What Is RAG, and Why Does It Matter? RAG — Retrieval-Augmented Generation — is one of the most widely used methods for enabling an AI system to answer not from general knowledge alone, but from specific, uploaded documents. In a law firm, this means the firm’s…
A guide to interpreting benchmark scores for non-specialists The Headline That Promises Everything and Explains Nothing It appears in some form almost every week: ‘The new X AI model is 40% better than its predecessor.’ Or: ‘AI model Y has surpassed human performance on benchmark Z.’ These statements are grounded in real measurements — but…
When your digital tool changes unilaterally — and there is nothing you can do about it The EU Sovereignty Wave: Background In recent months, Europe’s political and technology decision-makers have grown increasingly vocal about what they long treated as mere principle: digital independence is not ideology — it is a business and security necessity. The…
The right specialist for the right task — and what most job postings get wrong When a business leader decides it is time to bring AI into the company, the first instinct is almost always the same: “We need to hire an AI engineer.” LinkedIn listings, consultancy recommendations, and industry articles all push this term…
AI solutions are multiplying for lawyers, accountants and physicians. Their publishers promise time savings, GDPR compliance and transparent pricing. But between the price displayed on the website and what you actually pay at the end of the month, there can be a considerable — and barely verifiable — gap. This is not necessarily a question…
Cybercrime is not a future threat. It is happening now – every day, at industrial scale, requiring ever less technical expertise. This is not scaremongering: these are figures published by the commander of the French National Gendarmerie’s cyber unit. An industrialisation we can no longer ignore General Hervé Petry, commander of UNCyber – the French…
The Secret Architecture Behind the AI Tools You Already Use If you have heard that large AI models are made up of experts but had no idea what that actually means, this article is for you. Written for accountants, lawyers, doctors, and anyone who uses these tools without being an engineer. The Kitchen Analogy: Where…
You may have already tried “giving a document” to ChatGPT: you attach a contract, ask a question, the AI answers. It’s convenient. But you’ve probably noticed that by the next session, it has forgotten everything. You start again. You reattach the file. You ask the question again. There’s another approach: more efficient, more secure, and…
That’s the phrase we hear most often in professional offices. And it’s entirely understandable: ChatGPT Plus at €20/month works well, and nobody wants to hear about more complicated solutions. Except this question hides another, far more important one: €20 a month to do what, exactly? Because depending on what you expect from your AI –…
The secret of AI’s “short-term memory” The first time someone hears that an artificial intelligence model has a “context window,” they usually nod and move on. Then, a few weeks later, when the AI system starts behaving strangely – forgetting something mentioned five minutes ago, or confusing the beginning of a document with the end…
If you have ever seen AI models before installation, you have probably come across something like: “mistral-7b-instruct-v0.3.Q4_K_M.gguf”. The model name may ring a bell, we have already explained the meaning of the letter “b”, but what is that string of letters and numbers at the end?… That is quantization. A simple but clever technique that…
Word, PDF, Excel: what really happens behind the scenes You may have tried to “give a document to the AI” and wondered: does it actually read it? Does it understand my Excel spreadsheet? Does it see the layout of my Word contract? The short answer: no, not directly. And understanding why means understanding how artificial…
What really happens when your AI thinks When talking about computer performance, the usual reflex is to look at the processor: “how many GHz? how many cores?” This is logical for many tasks — video editing, gaming, running a complex spreadsheet. But for running a language model like those used by ArkeoAI, this logic is…
It is the basic unit an AI uses to read, understand, and write. You may have noticed that AI services talk about “tokens”: token limits, cost per token, context window in tokens… The word appears everywhere, but it is rarely explained clearly. Yet understanding what a token is means understanding how a language model perceives…
Understanding hallucinations in language models You may have already heard the term “hallucination” applied to artificial intelligence. A model that cites a law article that does not exist. An assistant that calculates a redundancy payment at €107,000 when the real amount is €2,625. A fabricated case law reference, written with the same confidence as a…
Concrete use cases, without excessive promises An accountant spends an average of 30 to 40% of their time on low-value-added tasks: documentary research, repetitive regulatory checks, formatting standard responses. AI does not replace expertise — but it can absorb a large part of this burden. Instant regulatory research Instead of manually browsing the General Tax…
It’s not a technology problem Studies keep multiplying: between 60 and 80% of corporate AI projects fail to meet their objectives. Yet the technology has never been more accessible. So where is the problem? Mistake #1: believing AI does everything on its own AI is a tool, not an autonomous employee. It amplifies what you…
Demystifying a phrase everyone uses but few truly understand “Offline artificial intelligence”, “local AI”, “on-premise model”… These expressions are increasingly common, but their concrete meaning remains unclear for many professionals. Here is what they actually mean. Online vs offline: the fundamental difference An online AI tool operates on remote servers. When you ask a question…
What you send to the cloud no longer truly belongs to you When a lawyer, notary, or accountant uses an online AI tool, something happens that many people are unaware of: the data entered — questions, document excerpts, client names — passes through external servers, often located outside the European Union. What the GDPR says…
When size doesn’t tell the whole story — and what the numbers actually mean If you’ve ever looked into artificial intelligence, you’ve almost certainly come across expressions like “7B model” or “20 billion parameter LLM”. But what do these numbers actually mean — and more importantly, are they really the most relevant criterion when choosing…