andrej karpathy
30 articles about andrej karpathy in AI news
Andrej Karpathy's LLM-Wiki Framework Solves AI Amnesia with Persistent Knowledge
Andrej Karpathy published a two-page framework called LLM-Wiki that transforms how AI systems handle accumulated knowledge. Instead of retrieving from raw documents each time, the AI compiles sources into its own structured wiki that persists across sessions.
Andrej Karpathy's Personal Knowledge Management System Uses LLM Embeddings Without RAG for 400K-Word Research Base
AI researcher Andrej Karpathy has developed a personal knowledge management system that processes 400,000 words of research notes using LLM embeddings rather than traditional RAG architecture. The system enables semantic search, summarization, and content generation directly from his Obsidian vault.
Andrej Karpathy: AI Industry Must Reconfigure for Agent-Centric Future, Not Human Users
Andrej Karpathy argues the AI industry's fundamental customer is shifting from humans to AI agents acting on their behalf, requiring substantial architectural and business refactoring.
Andrej Karpathy Builds 'Dobby the Elf Claw' Smart Home AI, Replacing 6 Apps with Natural Language Control
AI researcher Andrej Karpathy has built a personal smart home AI agent named 'Dobby the Elf Claw' that consolidates control of lights, HVAC, shades, pool, and security into a single natural language interface, eliminating the need for six separate apps.
Andrej Karpathy's 'Engineering's Phase Shift' Talk Covers AI Psychosis, Model Speciation, and a SETI-Style Movement
Andrej Karpathy's one-hour talk, highlighted by AI engineer Rohan Pandey, explores the shift from software to AI engineering, touching on AI psychosis, AutoResearch, and a potential distributed AI research movement.
Andrej Karpathy: AI Agent Failures Are 'Skill Issues,' Not Model Capability Problems
Andrej Karpathy argues most AI agent failures stem from poor user instructions and tooling, not model limitations. He advocates delegating 20-minute 'macro actions' to parallel agents and reviewing their work.
Andrej Karpathy's Deleted Tool: AI Exposure Scores for 342 Jobs, Finds $3.7T in High-Risk Wages
Andrej Karpathy briefly released a tool scoring 342 job types for AI exposure using an LLM, finding an average score of 5.3/10. The analysis identified $3.7 trillion in annual wages at high exposure (7+), with software developers at 9/10 and medical transcriptionists at 10/10.
Karpathy Joins Anthropic to Lead Recursive Self-Improvement Team
Andrej Karpathy joins Anthropic to lead a new recursive self-improvement team using Claude to accelerate pretraining, per @kimmonismus. The move signals a bet on synthetic data loops over brute-force scaling.
Karpathy: AI Industry Must Reconfigure for Agent-Centric Future
Andrej Karpathy states the AI industry must reconfigure as AI agents become the primary customers, not humans. This shift will require substantial architectural and business model changes.
Karpathy's LLM Wiki Hits 5k Stars, Gains Memory Lifecycle Extension
Andrej Karpathy's LLM Wiki repository gained 5,000 GitHub stars in two days. A developer has now extended it with memory lifecycle features, addressing a noted gap.
Karpathy-Inspired CLAUDE.md Hits 15K GitHub Stars for AI Coding Rules
A GitHub repo containing a single CLAUDE.md file, inspired by Andrej Karpathy's observations on predictable LLM coding errors, has reached 15,000 stars. It represents a move from simply using AI to write code to engineering its behavior for better output.
Developer Ships LLM-Powered Knowledge Graph Days After Karpathy Tweet
Following a tweet by Andrej Karpathy, a developer rapidly built and released a working implementation of an LLM-powered knowledge graph on GitHub, showcasing the speed of open-source AI development.
Karpathy's AI Research Agent: 630 Lines of Code That Could Reshape Machine Learning
Andrej Karpathy has released an open-source AI agent that autonomously runs ML research loops—modifying architectures, tuning hyperparameters, and committing improvements to Git while requiring minimal human oversight.
Karpathy's Autoresearch: Democratizing AI Experimentation with Minimalist Agentic Tools
Andrej Karpathy releases 'autoresearch,' a 630-line Python tool enabling AI agents to autonomously conduct machine learning experiments on single GPUs. This minimalist framework transforms how researchers approach iterative ML optimization.
Karpathy's 'Autoresearch' Tool Democratizes AI Research: One GPU, One Night, 100 Experiments
Andrej Karpathy has open-sourced 'autoresearch,' a tool that enables AI to autonomously improve its own training code. By writing simple prompts in Markdown, researchers can have AI agents run hundreds of experiments overnight on a single GPU, dramatically accelerating the research process.
Karpathy's Autonomous AI Researcher: Programming the Programmer in the Age of Agentic Science
Andrej Karpathy has open-sourced an autonomous AI research agent that can run ~100 experiments overnight without human supervision. The system turns research into a game with fixed-time trials, where prompt engineering replaces manual coding.
AI Agents Cross the Reliability Threshold: Karpathy Declares Programming Fundamentally Transformed
Former OpenAI researcher Andrej Karpathy declares programming has become "unrecognizable" as AI agents now reliably complete complex tasks in minutes rather than days. This fundamental shift occurred in late 2026 when agents achieved unprecedented reliability through improved model quality and task persistence.
AI Agents Now Training Other AI Models, Sparking Autoresearch Trend
AI agents are now being used to train other AI models, creating advanced agentic systems. This development stems from Andrej Karpathy's autoresearch repository and represents early-stage automation of AI research.
The Self-Improving AI Era Begins: GPT-5.4 and Autonomous Research Breakthroughs
OpenAI's GPT-5.4 release and Andrej Karpathy's autonomous AI research experiment signal a paradigm shift where AI systems can now improve their own underlying technology. This marks the beginning of closed-loop AI self-improvement.
Claude.md Hits 152K GitHub Stars; Karpathy Notes LLM Failure Patterns
Claude.md hits 152K GitHub stars. Karpathy notes LLMs fail consistently, driving demand for standardized prompt templates.
Karpathy: Neural nets will become the host, CPUs the co-processor
Karpathy predicts neural networks will become the host OS, with CPUs as co-processors, rendering most classical app interfaces obsolete.
Replace Karpathy's Agent Memory Automation with This 30-Line /close-day Hook
Background automation fails on laptops; use a simple /close-day skill and date tags in MEMORY.md instead.
Vibe coding leaves terminal; Google Cloud MCP server goes live
Google Cloud ships first major cloud MCP server, enabling AI agents to directly access Vertex AI, BigQuery, and Cloud Storage. Move validates MCP as standard for AI-to-infrastructure communication.
Stop Dumping Instructions Into CLAUDE.md — Use the 3-Layer Agent Harness
Stop appending rules to CLAUDE.md. Use the 3-Layer Agent Harness: a short constitution (CLAUDE.md), specialist skills, and subagents. This respects the 150-instruction compliance budget and keeps your agent reliable.
ByteDance Finds AI Agents Double Learning Speed Every 3 Months
ByteDance's Seed AI team discovered that AI agents double learning speed every three months via real-world interaction, per a Thursday paper. EdgeBench benchmark with 134 tasks ≥12 hours each underpins the finding.
Etched Hits $5B Valuation, $1B in Orders for AI Inference Chip
Etched hits $5B valuation with $1B in orders for TSMC-made inference chips, raising $500M from top investors. The startup targets Nvidia's dominance.
Noam Shazeer leaves Google for OpenAI after $2.7B Character.AI return
Noam Shazeer left Google for OpenAI months after returning via a $2.7B Character.AI deal, marking the second major AI talent move this year.
Stop Prompting Claude. Start Building Loops: Loop Engineering Explained
Loop engineering is the new paradigm: Claude Code's /goal command and CLAUDE.md let you encode autonomous workflows. Build verification layers and skill files to ship code without being in the loop.
GitHub Spec Kit: Open-Source Tool to Fix Vibe Coding’s Core Flaw
GitHub released Spec Kit, an open-source toolkit that enforces specification-first workflows for AI coding, addressing vibe coding's tendency to generate code before requirements are clear.
Claude Code's HTML Output Beats Markdown for LLM-Readable Docs
Claude Code generates HTML docs that LLMs parse more accurately than Markdown, per Thariq's analysis. Trade-off: harder for humans to edit.