Florent Daudens
I work to make AI accessible to everyone in journalism.
I work to make AI accessible to everyone in journalism.
I develop initiatives in open-source AI and journalism at Hugging Face 🤗.
Previously, I led teams of international, political, and daily news journalists at Radio-Canada, after having been the news director at Le Devoir, where we underwent a profound digital transformation. I notably established teams specialized in video and data visualization, and oversaw the launch of many innovative products (applications, newsletters, electoral coverages...), the development of new coverage areas, and the design of artificial intelligence projects.
In parallel, I have the pleasure of teaching digital journalism at the DESS in journalism at the University of Montréal. I am involved in the development of our profession with over the years participations on the board of the FPJQ and the magazine Trente, groups like Hacks/Hackers Montréal, etc. I have also worked at La Presse, Rue89, France3, and the Federation of Journalists of Québec.
To view my resume, click here.
This simple tool helps journalists optimize their articles for search engines. It is based on Llama 3 and can be adapted to other models. The prompt is also accessible.
To try the tool, click here.
In the "Digital Journalism" course at UdM, this year I am integrating a conversational robot as a course assistant. Using the Retrieval-augmented generation (RAG) method, this robot is designed to supplement the teachings with relevant information extracted from course transcripts.
This educational project allows students to interact directly with an advanced language model, thereby enriching their learning experience. I collect their feedback and questions in the system, exploring the impact of this AI assistant on the evolution of the course. A shared learning journey for both me and the students.
On the technological side, this program is based on GPT-4, LangChain, LangSmith, and Streamlit.
To try out the tool, click here. For more details on this project, read this post.
With a curiosity to explore ChatGPT's programming abilities, I crafted a program using Python, FeedParser, and OpenAI's API.
Hosted on AWS for automation, this program sends out an email at 8 a.m. daily, providing a summary of the past 24 hours' AI-related articles using text-davinci-003. You can find more details in this post.
Three objectives for this project:
For those who like to look under the hood, I've tested several solutions. The final configuration relies on a Pandas agent from LangChain, GPT-4 for the language model, Langsmith for interaction tracking, and Streamlit for deployment.
To try out the tool, click here. For more details on this project, see this post.
A simple tool to flood the Internet generate a Twitter thread (or the 24th letter of the alphabet) from news articles, and an opportunity to test LangChain Hub for prompts. This project uses:
To try out the tool, click here. For more details on this project, read this post.