– Les cartes : Leaflet
– L'API de cartographie : Google Earth Engine (c'est trop sous-coté, je vous jure, essayez si vous ne connaissez pas)
– Modèle fine-tuné : YOLOv8s
– Labellisation : custom tools en Node.js
– BDD : SQLite structuré, des dossiers sur mon ordi en non structuré
RESEARCH
-
YOLOv8s Fine-Tuning Workflow with Geospatial Data Pipeline
By
–
-
METR Tests Internal AI Agents for Deception and Accuracy
By
–
Your AI agent lied about its results. Not once. Routinely. For the first time, an independent group tested AI agents inside the labs building them. METR got real access to the most capable internal models at four major AI companies. Not the public versions. The actual ones
-
India Launches AIKosh Open AI Platform for Researchers and Startups
By
–
AIKosh is India’s open AI platform designed to make datasets, models, tools, and compute resources more accessible for researchers, startups, developers, institutions, and public sector innovation. Built under the IndiaAI Mission, AIKosh brings together AI resources in one place
-
Cohere Command A+: Parallel Block Architecture Innovation
By
–
You're paying for closed models when Cohere just dropped this for free.
— AlphaSignal AI (@AlphaSignalAI) 21 mai 2026
And the real story in Command A+ isn't the benchmarks.
It's the parallel block design.
Standard transformers run attention and feedforward layers sequentially. This model runs them side by side, same… https://t.co/PEMZNEzAN9You're paying for closed models when Cohere just dropped this for free. And the real story in Command A+ isn't the benchmarks. It's the parallel block design. Standard transformers run attention and feedforward layers sequentially. This model runs them side by side, same
-
Mixture-of-Experts Training: Emergent Specialization in AI Models
By
–
MoE Training, Part 1 — in one tweet:
— Satya Mallick (@LearnOpenCV) 21 mai 2026
You do NOT assign "this expert handles medicine, this one handles law."
You start with 9 random experts + a router. The router learns to pick 2–3 per question. Specialization emerges from data, not design.
That's how Mixtral and DeepSeek… pic.twitter.com/YGSc6ak94iMoE Training, Part 1 — in one tweet:
You do NOT assign "this expert handles medicine, this one handles law."
You start with 9 random experts + a router. The router learns to pick 2–3 per question. Specialization emerges from data, not design.
That's how Mixtral and DeepSeek -
OpenAI Solves an Erdős Problem
By
–
OPENAI MAKES A MATH BREAKTHROUGH! Continuing the rapid advancement of AI in mathematics, an internal OpenAI model has successfully solved what is, to date, the most significant Erdős problem ever addressed autonomously. The historical importance of this solution
-
AutoResearchClaw: Autonomous AI Research with Collaboration
By
–
AutoResearchClaw: Self-Reinforcing Autonomous Research with Human-AI Collaboration As real-world science is iterative, this paper introduces AutoResearchClaw, a multi-agent system that debates ideas, self-corrects experiments, decides whether to pivot or refine, verifies data, and
-
DECS fixes LLM overthinking by cutting redundant tokens
By
–
Overthinking is killing LLM reasoning efficiency. DECS fixes it by surgically cutting redundant tokens without hurting performance. Current RLVR models generate excessively long reasoning paths with zero gain. Existing length penalties backfire—they penalize essential
-
OpenAI model disproves 80-year-old Erdős unit distance conjecture
By
–
OpenAI made history today. An internal reasoning model autonomously disproved a famous conjecture in mathematics that stood for nearly 80 years. The problem: In 1946, Paul Erdős asked how many pairs of points can be exactly 1 unit apart if you place n points on a flat surface.
-
AI Alignment for Human Flourishing Research Paper
By
–
Positive Alignment: Artificial Intelligence for Human Flourishing Laukkonen et al.: https://
arxiv.org/abs/2605.10310 #ArtificialIntelligence #AIAgents