BREAKING : Claude vient de révolutionner la moitié d'internet. Il peut maintenant planifier des projets, automatiser des workflows, rédiger des rapports et résoudre des tâches complexes comme un COO à 500€/h (gratuitement). Voici 12 prompts Claude pour accomplir des mois de
CODE
-
AI agents run autonomous ML research experiments
By
–
Karpathy just dropped a 630-line repo where AI agents run their own ML research experiments in an infinite loop.
— God of Prompt (@godofprompt) 9 mars 2026
No human involved. Every dot on that graph is a full training run the agent did on its own, finding better architectures, tuning hyperparameters, committing… https://t.co/pW1GCs5hC2Karpathy just dropped a 630-line repo where AI agents run their own ML research experiments in an infinite loop. No human involved. Every dot on that graph is a full training run the agent did on its own, finding better architectures, tuning hyperparameters, committing
-
Andrej Karpathy releases Autoresearch for autonomous ML experimentation
By
–
Wow. @karpathy just open-sourced 'Autoresearch' AI that trains AI, on loop. 100 ML experiments overnight over a single GPU! Written, run, and iterated by an agent. Your only job: maintain a single Markdown file: ✦ What to explore
✦ What to prioritize
✦ What tradeoffs -
AI and LLMs Workshop Success: Register for Upcoming Machine Learning Training
By
–
Thank you to everyone who joined our Introduction to AI and Large Language Models (LLMs) workshop last week! 🤖 Are you based at @Cambridge_Uni and interested to develop practical machine learning skills for research? Sign up for an upcoming workshop: training.cam.ac.uk/apsci/sea…
-
Seeking Feedback on Deepagents Deployment Documentation
By
–
Be future-ready with this book >> "Quantum #MachineLearning and Optimization in #Finance" (494 pages; 2nd Edition): http://
amzn.to/4lNlBt5 v/ @PacktDataML -
Langchain Deepagents Deployment Documentation and Feedback Request
By
–
Los Angeles Marathon 2026 photo-finish: https://t.co/qvADpCe7XU
— Kirk Borne (@KirkDBorne) 9 mars 2026Los Angeles Marathon 2026 photo-finish:
-
Agent Observability for Agent Improvement Loops
By
–
A Gentle Introduction to Optimization http://
amzn.to/3MQ6fE5
—————
#Mathematics #PrescriptiveAnalytics #ORMS #DataScience #ML #MachineLearning -
Codex acceleration in the last week with GPT 5.4, Windows, and new skills
By
–
Codex in *just* the last week: > GPT 5.4
> Codex for Windows
> Fast mode
> Skills – Playwright Interactive, Slides, Spreadsheets and more Non app related but relevant: > Codex Security
> Codex for OSS Can you feel the acceleration, anon? -
Replit Core: Gift 1 Month, Get 1 Month Free for International Women’s Day
By
–
This International Women’s Day, we’re celebrating the builders & dreamers in our community Gift 1 month of Replit Core.
Get 1 month free (or $20 in credits). Enjoy today, we’ve got the next month covered. Offer ends today → -
Building Coding Agents for Terminal: Key Lessons
By
–
Nice paper on lessons around building coding agents for the terminal.