Testing Karpathy's Autonomous Research Loop on CPU Architecture Optimization
Contribute to FeSens/auto-arch-tournament development by creating an account on GitHub.
Read the full articleYou might also wanna read
Karpathy Autoresearch: Autonomous AI Experiments Overnight
Andrej Karpathy's 630-line autoresearch script lets AI agents run hundreds of ML experiments while you sleep. Here's what it means for AI en
Autoresearch Workflows: Automating ML Training with RL Agents and NVIDIA NeMo
Coding AI agents are becoming practical operators for long-running machine learning (ML) workflows. They can inspect repositories, set up ru
developer.nvidia.com·1d ago
AutoResearch: Bringing Reliability to AI-Driven Scientific Workflows
AutoResearch aims to fix the reliability issues plaguing AI-driven scientific research. By combining code execution, citation checks, and it
Anthropic's path toward recursive self-improvement in AI development
Our progress toward recursive self-improvement, and its implications.
anthropic.com·1mo agoWhat if an AI agent could run its own LLM training experiments overnight? In this article, Ishaan walks you through Andrej Karpathy’s autoresearch project. You'll learn how the agent edits runs fixed
What if an AI agent could run its own LLM training experiments overnight? In this article, Ishaan walks you through Andrej Karpathy’s autore
AgentKernelArena: Benchmarking AI Coding Agents for GPU Kernel Optimization on AMD Instinct GPUs
AI coding agents such as Cursor Agent, Claude Code, and OpenAI Codex are improving fast, and people increasingly trust them with specialized
Comments
Sign in to join the conversation.
No comments yet. Be the first.