Microsoft : 30 % de tout le code est écrit par l’IA
Google : 30 % de tout le code est écrit par l’IA On peut raisonnablement supposer qu’à la fin de 2025, ce sera autour de 50 %.
CODE
-
AI Writes 30% of Code at Microsoft and Google in 2025
By
–
-
MCP and CodeLLM: Building Features in One Shot
By
–
See what you can do with MCP and a good coding agent combined. CodeLLM in action – build a feature request in one shot.
-
Why Learning to Code Remains Essential in the AI Era
By
–
"You should still learn to code" needs an asterisk. The SWE job is changing fast. By the time you're proficient, today's landscape will be history. But that's exactly why you should start learning now: coding is ground zero for human-AI collaboration. Through learning to code,
-
DeepSeek-Prover-V2: Open-Source Lean 4 Theorem Proving LLM
By
–
More details on DeepSeek-Prover-V2!
It comes in two sizes: 7B & 671B, and yes — the 7B variant beats Kimina-Prover Preview 72B! DeepSeek-Prover-V2 is an open-source LLM for formal theorem proving in Lean 4, initialized using a recursive pipeline powered by DeepSeek-V3. -
Hugging Face’s smolagents: Tiny, focused agentic framework tackles complexity.
By
–
The agentic framework of @huggingface
, smolagents, is the tinyest ever. It has fewer features than other frameworks -> that's exactly its goal. The main issue among agentic frameworks is complexity : they tend to pile up abstractions, trying to solve everything rather than being -
Learning Python with Modern AI Tools and LLM Platforms
By
–
Thanks! It's fun finally having some tangible ways to test what I've learned. So many great uses! I first wanted to learn Python way back in 2010, but it was still mostly manuals or pricey courses. Now CodeAcademy, ChatGPT, and other LLM platforms like Google Colab help a lot!
-
Building MCP Servers in Python: Best Practices
By
–
Is this easiest way to build an MCP server in Python?
-
DocentPro Uses LangGraph for AI Travel Planning System
By
–
How DocentPro powers AI trip planning with LangGraph @docentpro_sf is building an AI travel assistant that helps users go from idea → itinerary → booking. Using LangGraph + LangSmith, they’ve created a modular multi-agent system that handles discovery, planning, and real-time
-
Browser Use: AI Agents Web Integration with Python
By
–
Make websites accessible for AI agents! Browser Use is the easiest way to connect your AI agents to the web with just a few lines of Python code. 100% Open Source
-
Length-Controlled AlpacaEval: Debiasing Automatic AI Evaluators
By
–
Length-Controlled AlpacaEval: A Simple Way to Debias Automatic Evaluators Dubois et al.: https://
arxiv.org/abs/2404.04475 #ArtificialIntelligence #DeepLearning #MachineLearning