Lisez bien. D'ici juin au plus tard, j'aurai terminé un processus très compliqué et démarré il y a un bon moment, qui m'aura coûté un bras, je vais posséder ma propre IA et mes propres LLMs qui ne dépendront plus d'aucun autre provider extérieur. J'ai encore assuré mon
GENERATIVE AI
-
Enhance Generative AI with RAG and Internal Data
By
–
Unlocking Data with #GenerativeAI and RAG — Enhance Generative AI systems by integrating internal data with large language models using RAG: http://
amzn.to/3PtFHdv v/ @PacktDataML -
Design Scalable Generative AI with LangChain and Vertex AI
By
–
Generative AI on Google Cloud with LangChain — Design scalable Generative AI solutions with Python, LangChain, and Vertex AI on Google Cloud: http://
amzn.to/4frbkPA v/ @PacktDataML 𝓚𝓮𝔂 𝓕𝓮𝓪𝓽𝓾𝓻𝓮𝓼:
Turn challenges into opportunities by learning advanced techniques for -
New book: RAG-Driven Generative AI (2nd ed.)
By
–
New Release (2nd edition) from @PacktDataML available at http://
amzn.to/4tULP1b RAG-Driven Generative AI — Build MAS-RAG with DualRAG, GraphRAG, multimodal video pipelines, and Oracle Database 23ai 𝗞𝗲𝘆 𝗙𝗲𝗮𝘁𝘂𝗿𝗲𝘀:
Master DualRAG by combining vector search with SQL -
Building iPhone Apps with Codex in 2026
By
–
I really love building iPhone apps in Codex. Codex can design the screens, write the Swift code with GPT-5.5, run the app in Simulator without opening Xcode, and even click around with computer use to test it!
-
Swift iPhone Development with AI Tools
By
–
Same! Building iPhone apps in Swift is still one of my favorite things to do in Codex. These days I do it all there: GPT-Image-2 for the design, GPT-5.5 for the code, then ask Codex to run it in Simulator without opening Xcode. Hard to beat!
-
The day after General Artificial Intelligence (AGI)
By
–
I have published an episode on @ivoox
: "#off-topic18: The day after General Artificial Intelligence (AGI) #podcast -
Chronological list of baffling OpenAI model names
By
–
The great thing is that the names are so baffling that the most important models OpenAI released were names davinci-002, GPT-3.5, GPT-4, o1-preview, o3, GPT-5 Pro, and you would never know the ways they are connected (my listing was chronological)
-
New AI-Driven Workflow for HTML Generation
By
–
Anthropic's Thariq's article on HTML from yesterday blew up, with 1.5M reads. It looks like it's talking about formatting aesthetics, but actually he's describing an entirely new workflow. Picking out a few of the points with the most technical depth. First, HTML isn't a
-
Sakana AI Accelerates Sparse LLMs with NVIDIA
By
–
Sakana AIは、@NVIDIAとの共同研究で、スパースなTransformer言語モデルの推論・学習を高速化する新しいGPUカーネルとデータ形式を開発しました。
— Sakana AI (@SakanaAILabs) 9 mai 2026
ブログ：https://t.co/fMARMRFsJJ
LLMのコストの大部分を占めるフィードフォワード層では、実は各トークンに対して大半の活性がほぼゼロで無駄な計算に… https://t.co/nTMg0QgdSrSakana AI has developed new GPU kernels and data formats that accelerate inference and training of sparse Transformer language models through joint research with @NVIDIA
. Blog: https://
pub.sakana.ai/sparser-faster
-llms/
… In the feedforward layers, which account for the majority of LLM costs, most