GPT-5 prompting guide | OpenAI Cookbook
GPT-5, our newest flagship model, represents a substantial leap forward in agentic task performance, coding, raw intelligence, and steera...
With GPT-5, OpenAI shifts its prompting preference from markdown to XML. Meanwhile, Anthropic — long associated with XML-style prompting — moves its new Agent Skills (SKILLS.md) to markdown. Prompting “best practices” never seem to meet in the middle. www.anthropic.com/engineering/...
13.11.2025 14:30 — 👍 0 🔁 0 💬 0 📌 0
YouTube video by Applied AI - GenAI, ChatGPT et LLM-powered apps
À la découverte d’Agents SDK, le nouveau framework IA d’OpenAI
My latest video is on #AgentsSDK, part of the new tools for building AI Agents from #OpenAI www.youtube.com/watch?v=rBfG...
25.03.2025 14:39 — 👍 0 🔁 0 💬 0 📌 0
Aiguilles des Arves
18.02.2025 15:37 — 👍 0 🔁 0 💬 0 📌 0
Massif des Arves
18.02.2025 15:36 — 👍 0 🔁 0 💬 1 📌 0
17.02.2025 20:55 — 👍 0 🔁 0 💬 0 📌 0
On the starting line for the white trail of valloire galibier in Alpes. 10km night trail on snow.
17.02.2025 17:16 — 👍 0 🔁 0 💬 1 📌 0
Many people have asked me about the France Action Summit.
I think a summit is typically most valuable as a catalyst, not as a solution in itself.
But, will share some observations.
13.02.2025 09:08 — 👍 42 🔁 10 💬 2 📌 2
Créer un Système Multi-Agent pour Rédiger des Scripts YouTube avec LangGraph et Mistral Small 3
YouTube video by Applied AI - GenAI, ChatGPT et LLM-powered apps
🔴 Today Live at 1 PM CET – Building an Agentic Workflow with LangGraph and Mistral 3 Small
I’ll walk through my hands-on “Building an Agentic System for YouTube Script Writing” live and in French. Step-by-step guide to creating your first agentic workflow!
📺 Watch live: youtube.com/live/0KY-73m...
10.02.2025 08:46 — 👍 0 🔁 0 💬 0 📌 0
agentic-script-writer
Want to build an AI agent for scriptwriting? I created a step-by-step tutorial on #LangGraph + #MistralAI 3 Small to automate research, writing & improvement. Check it out!
📖 Tutorial: bittnerpierre.github.io/AI-Agent-Cas...
Let me know if this format is useful!
06.02.2025 17:14 — 👍 0 🔁 0 💬 1 📌 0
Turns out, I just learned about Musk & Grimes’ three sci-fi-named kids… from Wikipedia. All because I was reading about her statement after Musk’s controversial salute amid social tax issues. Guess we all have our own blind spots. 🤷♂️
04.02.2025 15:47 — 👍 0 🔁 0 💬 0 📌 0
My wife knows that Grimes had three kids with Elon Musk, all with names straight out of a sci-fi novel… but she has no idea what NVIDIA is—the world’s biggest market cap right now. Priorities, I guess. 🤷♂️
04.02.2025 11:38 — 👍 2 🔁 0 💬 1 📌 0
03.02.2025 21:46 — 👍 0 🔁 0 💬 0 📌 0
Mistral models have always been strong in function calling, and Small 3 refines it even further. Tested with #LangGraph + #LangChain, and processing time was cut in half—all while maintaining high-quality structured script generation. Open models at this level push AI automation forward.
31.01.2025 06:57 — 👍 0 🔁 0 💬 1 📌 0
This release is notable step-forward for #AgenticAI workflows. I was able to replace Mistral Large in critical parts of my multi-agent setup with no drop in quality. Long-context handling is way more robust, and structured outputs stay precise even over extended inputs.
31.01.2025 06:57 — 👍 0 🔁 0 💬 1 📌 0
Mistral Small 3
Apache 2.0, 81% MMLU, 150 tokens/s
🚀 Mistral Small 3 is here! Open-source, 24B parameters, Apache 2.0 license—smaller, faster, cheaper, and delivering stunning results. I’ve been following #MistralAI since its beginning and made it my main model for personal projects since late last year. mistral.ai/news/mistral...
31.01.2025 06:57 — 👍 0 🔁 0 💬 1 📌 0
Hello Brussels!
25.01.2025 13:08 — 👍 0 🔁 0 💬 0 📌 0
The 2nd issue is why I fall into the 1st one as I was looking for a workaround to integrate llama index along LC and LG in my current project.
24.01.2025 17:49 — 👍 0 🔁 0 💬 0 📌 0
This week, I’ve made some very modest contributions to open source ai project by reporting mistral related issues. One on llama-index and one on mistral llm itself.
24.01.2025 17:49 — 👍 0 🔁 0 💬 1 📌 0
Back at Station F tonight in Paris for the AI Developer Meetup organized by #Koyeb and #Neo4J. Featuring #HuggingFace, ZML and Sophia Yang from #MistralAI. Let me know if you’re attending!
16.01.2025 18:06 — 👍 0 🔁 0 💬 0 📌 0
YouTube video by Applied AI - GenAI, ChatGPT et LLM-powered apps
2025 : L'Année où l'IA va TOUT changer (et les maths le prouvent)
Check out my latest video with my New Year's wishes: "2025: The Year AI Changes EVERYTHING (And Math Proves It)" (in french) youtu.be/QM3MgiqZPHc
16.01.2025 14:40 — 👍 0 🔁 0 💬 0 📌 0
The link redirect to x. Could you share the right link, please?
08.01.2025 17:23 — 👍 0 🔁 0 💬 1 📌 0
El Campello beach near Alicante (Spain)
03.01.2025 10:36 — 👍 1 🔁 0 💬 0 📌 0
Benidorm
03.01.2025 10:25 — 👍 0 🔁 0 💬 0 📌 0
Hey #BlueSky, my new video on #LangGraph and #IA agentics workflows is available on #Youtube (in French). I hope you’ll enjoy it. youtube.com/watch?v=_rct...
29.12.2024 07:04 — 👍 0 🔁 0 💬 0 📌 0
research @ Google DeepMind
Breaking distributed systems, one fault at a time.
[bridged from https://mastodon.jepsen.io/@jepsen on the fediverse by https://fed.brid.gy/ ]
Writer of books (http://themissingreadme.com), code (http://slatedb.io), checks (http://materializedview.capital), and newsletters (http://materializedview.io)
We're an Al safety and research company that builds reliable, interpretable, and steerable Al systems. Talk to our Al assistant Claude at Claude.ai.
Living in Kharkiv, Ukraine. Contributing to Ukrainian voices online | support me : PayPal: kate.boguslavskaya@gmail.com | http://buymeacoffee.com/kateinkharkiv
Author of 📘 LangChain for JavaScript developers: http://js-craft.io/book
I like computers. I try to make them like me back. More than computers I like humans.
Google Chief Scientist, Gemini Lead. Opinions stated here are my own, not those of Google. Gemini, TensorFlow, MapReduce, Bigtable, Spanner, ML things, ...
🇵🇭 Illustrator (Marvel, MtG, DC, etc.!)
📧hello@rianbowart.com
🎨WEBSITE: https://rianbowart.com/
🌈PATREON: http://patreon.com/rianbowart
✨Find me elsewhere! https://bio.site/rianbowart
Journaliste à @ouest-france.fr, rédactrice en chef déléguée en charge des #Outremer
Chaîne WhatsApp Outre-Mer par Ouest-France https://urls.fr/wJGiI0
Co-founder & Chief Scientist at Yutori. Prev: Senior Director leading FAIR Embodied AI at Meta, and Professor at Georgia Tech.
San Diego Dec 2-7, 25 and Mexico City Nov 30-Dec 5, 25. Comments to this account are not monitored. Please send feedback to townhall@neurips.cc.
PhD Student at Johns Hopkins University. Previously: Allen Institute for AI, Apple, Samaya AI. Research for #NLProc #IR
Research Scientist @ Mosaic x Databricks. Adaptive Methods for Retrieval, Generation, NLP, AI, LLMs https://mrdrozdov.github.io/
assistant professor in computer science / data science at NYU. studying natural language processing and machine learning.
doing ML stuff at answer.ai / fast.ai
🇯🇵-based 🇫🇷man
27, French CS Engineer 💻, PhD in ML 🎓🤖 — Guiding generative models for better synthetic data and building multimodal representations @LightOn
Sentence Transformers, SetFit & NLTK maintainer
Machine Learning Engineer at 🤗 Hugging Face
Ph.D. student at University of Washington CSE. NLP. IBM Ph.D. fellow (2022-2023). Meta student researcher (2023-) . ☕️ 🐕 🏃♀️🧗♀️🍳