17 entries
Keyword: andrej-karpathyX post:pili 🪴
A new open-source agent skill instructs language models to write in ASD-STE100 Simplified Technical English. Originally designed for aerospace documentation, the controlled language forces AI outputs to be concise, direct, and unambiguous.
6kbookmarks307.4kviews
X post:nicco
A post by nicco highlights remarks by Andrej Karpathy asserting that prompting is an ephemeral interface and that graph architectures represent the true architectural layer for agent workflows. It pairs this with a practical guide by seeco on replacing sequential agent chains with explicit graphs.
529bookmarks58.5kviews
X post:Mahax
Mahax cites Andrej Karpathy's claim that prompting is disappearing in favour of graphs, and provides a practical guide on graph engineering with Claude to optimise AI agent workflows.
2.4kbookmarks240.8kviews
X post:Mr. Buzzoni
Mr. Buzzoni (@polydao) outlines a file-based harness and directory architecture for Claude Code that enables AI agents to execute overnight tasks autonomously. Using clear contracts, verification rubrics, state tracking, and documented receipts, the setup is designed to run predictably without manual night-time interventions.
373bookmarks29.7kviews
Repository:multica-ai/andrej-karpathy-skills
This repository provides a single CLAUDE.md configuration file designed to improve Claude Code's performance. It translates Andrej Karpathy's observations on common LLM coding pitfalls into four actionable instructions to reduce overengineering and unintended code edits.
210.3kstars
Link:Andrej Karpathy
The personal portfolio and resource hub of AI researcher Andrej Karpathy outlines his career milestones, teaching materials, talks, and open-source projects.
From Video: Weekly AI Updates: Model Releases, Agent Harnesses, and Developer Tooling (August 2026)
Article:Agrici Daniel
Agrici Daniel introduces claude-obsidian, a free open-source plugin for Claude Code. It implements Andrej Karpathy's LLM Wiki pattern to automatically compile and link Obsidian vaults from raw documents without requiring a vector database.
From Video: Weekly AI Updates: Local Models, GPT-6 Astra, and Agent Architectures
Article:latent.space
An editorial recap by Latent Space examines how every stage of the machine intelligence pipeline has shifted from human-created to model-created components since 2022. From reward signals and synthetic training corpora to self-directing curricula, automated researchers, and simulated environments, AI simulation is systematically replacing human inputs. The driving factor across all stages has been reliable verification, leaving the physical world as the final barrier.
From Video: AI Weekly Updates: Open-Source Model Surge, Agent Harnesses, and Meta's AI Reality Check
Article:Wyndo
Inspired by an idea from Andrej Karpathy, author Wyndo outlines a workflow using Claude Code and Obsidian Skills to automatically compile, cross-link, and maintain a personal knowledge base.
Article:Sam McVeety, Amir Hormati
Google Cloud has announced the Open Knowledge Format (OKF) v0.1, an open and vendor-neutral specification that standardises the LLM-wiki pattern into a portable format. OKF represents enterprise metadata, context, and curated knowledge as a directory of Markdown files with YAML frontmatter, readable by both humans and AI agents without proprietary SDKs.
From Video: Weekly AI Updates: GPT 5.6, Claude Sonnet 5, and Ornith
Link:Emmimal P Alexander
Emmimal P Alexander replaced an agentic LLM-based personal wiki with a pure Python compiler. The tool processes raw text notes into a linked markdown wiki deterministically, without API calls, embeddings, or third-party dependencies.
From Video: Weekly AI Updates: Model Releases, Prompt Tricks, and Agent Architectures
Repository:AgriciDaniel/claude-obsidian
claude-obsidian is an MIT-licensed open-source project that connects Claude Code with Obsidian into a self-organizing knowledge graph. Implementing Karpathy's LLM Wiki pattern, it maintains a structured vault made entirely of local plain Markdown files.
14.6kstarsPython
From Video: Weekly AI Updates: Local Models, GPT-6 Astra, and Agent Architectures
Repository:karpathy/nanoGPT
nanoGPT by Andrej Karpathy is a lean and fast codebase designed for training and fine-tuning medium-sized GPT models in PyTorch. Developed as a rewrite of minGPT, it can reproduce GPT-2 (124M). As of November 2025, the repository is officially marked as deprecated by the author, who recommends nanochat instead.
62.8kstarsPython
From X post: Weekend Project: Training a GPT-2-Level Model from Scratch
X post:Sizer
A viral post by Sizer promotes a two-hour lecture by Andrej Karpathy, claiming it covers agents, loops, graphs, and self-improving systems. However, commenters point out the video is actually an older presentation on basic daily LLM usage. The post also links to an article on orchestrating hundreds of sub-agents using context graphs.
1.7kbookmarks127.1kviews
X post:0xSero
In a post on X, 0xSero outlines a weekend project aimed at training a GPT-2-level language model using Python. According to the author, the setup requires around 4 to 8 hours and roughly $50 in compute costs, leveraging Andrej Karpathy's educational resources.
1.2kbookmarks69.1kviews
X post:vartekx
In an X post and guide, vartekx examines the shift from prompt engineering to context and loop engineering. Drawing on frameworks by Andrej Karpathy and Boris Cherny as well as an Anthropic engineer demo, the author details how disciplined context management powers persistent, self-healing AI agents.
59bookmarks6.5kviews
VideoVideo:Matthew Berman
Matthew Berman analyses Anthropic's new 'Claude Tag' integration. Acting as an ambient team member inside Slack with org-wide context, the tool promises massive productivity gains but poses serious risks of context lock-in and platform dependency, according to Berman.
17 of 17 shown
Do you have an interesting article, a video, or a tweet that belongs in our knowledge base? Write to us at office@webconsulting.at.
Parts of this content were created with the assistance of AI.
