European Parliament expands access to their archives with Claude in Amazon Bedrock
3:25

European Parliament expands access to their archives with Claude in Amazon Bedrock

Anthropic 21.10.2024 6 620 просмотров 259 лайков обн. 18.02.2026
Поделиться Telegram VK Бот
Транскрипт Скачать .md
Анализ с AI
Описание видео
The European Parliament is revolutionizing access to its vast historical archives by implementing 'Ask the EP Archives', also known as Archibot, an AI-powered tool built with Claude in Amazon Bedrock that allows users to instantly search, retrieve, and understand decades of legislative documents and parliamentary proceedings in multiple languages. Learn more: https://www.anthropic.com/customers/european-parliament

Оглавление (1 сегментов)

  1. 0:00 Segment 1 (00:00 - 03:00) 412 сл.
0:00

Segment 1 (00:00 - 03:00)

preserving Collective memory is one of the fundamentals of democracy welcome to the archive of the European Parliament the AR unit is in charge of U preserving managing and processing all the documents that have been produced and received by the European Parliament since 1952 we have documents related to the legislation internal Administration all the plary documents I can find resolutions that the parliament has been taken positions of the parliament in past or like the negotiations with the other institutions we started with 10,000 of documents we moved to hundred of thousands now we are to millions of document we decided to provide a way to navigate inside a huge document set there rival of generative AI is something that was a real shift arot is a simple and intuitive tool that help us and the researcher to find documents and to build reports based on the documents it's available on our website we have users uh from Gabon and from Australia can be accessed from everywhere we build arot using hopic clone technology and there was one point that got our attention this is constitutional AI we wanted that the answer provided by the large language model is a trust forthy answer the most important thing for us is trust we wanted to make sure about one thing if we use generative AI we permanently need to be under control of the solution that we've built we didn't want to have any data that could be collected or extracted for other purposes we absolutely want that people know where the information is coming from previously we had only the French as a language if you use so we needed to move multilingual so that all countries could have an access to our archives accuracy reliability and the multilinguism capacities are for us crucial I can't imagine honestly how much time it is saving because yeah the archives are huge as a researcher it makes my work way easier it's also way more easy for polic makers Educators and whoever is interested within the European Parliament we have shown that we can use generative AI in a controlled way this wi lism and the some in capacity of huge document sets was really a shift from generative AA in our domain the access to information and all the tools we provide in order to be able to make use of this information are really the foundations of a democratic project

Ещё от Anthropic

Ctrl+V

Экстракт Знаний в Telegram

Транскрипты, идеи, методички — всё самое полезное из лучших YouTube-каналов.

Подписаться