cd/entity/Karpathy· home entities Karpathy
grep -l @karpathy /news/*.json | wc -l → 20

Karpathy

mentions 20 type Organization feed RSS

// recent coverage 20 mentions

12:32
2026-06-28
dev.to
large-language-models

A Four-Type Framework for LLM Wiki by karpathy

A developer building a personal knowledge base using Karpathy's LLM Wiki framework discovered that storing only declarative knowledge (facts and definitions) is insufficient for expert-level reasoning…

00:00
2026-06-23
posthog.com
ai-agents

What is a Scout? A technical deep dive

PostHog introduces 'scouts' as small autonomous agents that monitor product data and emit signals for action, forming a core part of its self-driving pipeline now in open beta. Scouts use markdown-bas…

02:08
2026-06-22
sakana.ai
artificial-intelligence

Sakana Fugu

An AI agent using the AutoResearch framework autonomously improved a small GPT's training recipe over 123 experiments on a single H100 GPU, achieving a best mean bits-per-byte (BPB) of 0.9774 ± 0.0019…

09:48
2026-06-21
dev.to
developer-tools

Vibe coding is not a level. It's an axis.

A developer argues that 'vibe coding' autonomy levels (L0-L5) are incomplete without a second axis: operator discipline, which measures how much work survives session boundaries as inspectable state. …

12:02
2026-06-15
strangeloopcanon.com
large-language-models

LLM councils show groupthink

An experiment testing LLM councils found that they suffer from groupthink, retaining only about a quarter of unique, high-quality ideas from individual models while favoring consensus ideas. The peer-…

03:05
2026-06-14
austinhenley.com
artificial-intelligence

Automating my job away

A developer at Microsoft describes how adopting a policy of automating any task done more than twice led to unexpected consequences, including increased context switching and errors, but ultimately en…

09:54
2026-06-13
dev.to
artificial-intelligence

Build Your Own Shakespearean LLM

A developer built a character-level language model from scratch using Shakespeare's complete works, training a nanoGPT model on a consumer-grade MacBook Pro in about 15 minutes. The project demonstrat…

23:42
2026-06-10
gist.github.com
large-language-models

Building a personal wiki from your own digital exhaust

A developer built a personal wiki from their digital exhaust by processing 55 export directories into ~2,750 structured markdown pages. The project normalizes data from dozens of services into a unifi…

17:05
2026-06-08
aaif.io
ai-agents

Karpathy’s LLM Wiki as Agent Memory

Andrej Karpathy's LLM Wiki design is being adopted as an external memory architecture for AI agents, mapping raw source documents into a structured markdown knowledge base. The system uses three layer…

02:55
2026-06-03
betocmn.com
artificial-intelligence

Back to the Metal

Software engineers are shifting their focus from high-level abstractions to foundational computing skills, driven by the rapid advancement of agentic coding tools like Claude Code and Codex that outpe…

23:42
2026-06-02
dev.to
ai-tools

How I use pluckmd to read blogs with an AI agent

A developer created pluckmd, a CLI tool that extracts blog articles into markdown without per-site configuration, to enable AI agents to read and index web content. The tool automatically handles Java…

21:18
2026-05-27
letsdatascience.com
large-language-models

Karpathy LLM Wiki Search Evolves to Reduce Token Waste

Andrej Karpathy's LLM Wiki has evolved its search methodology to eliminate token waste caused by agents retrieving entire files for single relevant sections. The system now uses targeted retrieval to …

16:48
2026-05-25
twitter.com
artificial-intelligence

Anthropic onboarding day: Michael Scott introducing Karpathy

Anthropic held an onboarding day where a speaker was introduced in a manner compared to Michael Scott introducing Karpathy. The event's details were not accessible due to JavaScript being disabled in …

07:57
2026-05-20
gist.github.com
large-language-models

LLM Wiki V3: Compartmentalized Wiki Architecture

The article introduces LLM Wiki V3, a concept document that proposes a "compartmentalized wiki architecture" for scaling LLM-maintained knowledge systems. It argues that stateful LLM systems are built…

08:22
2026-05-11
gist.github.com
developer-tools

TokenZip v2 — PRD, HLD, LLD

TokenZip v2 is a token compression engine that reduces LLM input token costs by up to 95% for coding copilots like Claude Code and Codex by transforming an entire codebase into a multi-level, queryabl…

21:08
2026-02-11
gist.github.com
machine-learning

microgpt

`microgpt.py`, a minimal, dependency-free Python implementation of a GPT (Generative Pre-trained Transformer) model for training and inference. It includes a complete autograd system, a character-leve…

// co-occurs with top 8 entities