In practice8 min read
RAG: connecting a model to your organisation's data
Retrieval plus generation is the most common architecture for making a model answer from your documents. The hard part is not the model — it is the retrieval.
Read onBlog
Artificial intelligence, explained without the hype
Articles about how these systems work, how they are evaluated, what obligations they bring and where they fail. No unsourced figures and no promises nobody can check.
5 articles
- In practice6 min read
Prompting, RAG or fine-tuning: how to choose
Three approaches that are often confused and solve different problems. The wrong choice means a month of work for something that took a day — or the other way round.
Read on - In practice6 min read
Choosing a use case worth pursuing
Most AI projects fail before they start, at the moment the wrong problem is chosen.
Read on - In practice6 min read
The real cost of an AI project
The cost of model calls is usually the small part. Budgets break in places nobody puts in the initial estimate.
Read on - In practice6 min read
Open and closed models: what actually matters in the choice
\u201cOpen source\u201d means very different things in this field. For an organisation, the useful question is not ideological but operational.
Read on
Editorial note: Articles on this blog explain mechanisms and methods. They do not describe the association's projects and contain no figures or studies we cannot point to. The field moves quickly — the publication date matters.