AI Wiki — Knowledge Base

Gary Marcus 又放大招了！他直接把 Claude Code 源码泄露后的核心真相点破： ✅ Claude Code 是 LLM 时代以来最大进步 ✅ 但它根本不是纯 LLM，也不是纯深度学习 ✅ 核心文件 print.ts 足足 3167 行，塞满了 if-then …

Gary Marcus 又放大招了！他直接把 Claude Code 源码泄露后的核心真相点破： ✅ Claude Code 是 LLM 时代以来最大进步 ✅ 但它根本不是纯 LLM，也不是纯深度学习 ✅ 核心文件 print.ts 足足 3167 行，塞满了 if-then 分支 + 确定性符号逻辑 Anthropic 在关键时刻还是靠经典符号 AI来保底，才让 Agent 真正可靠。这波操

model-releasesgary-marcus--x

11 Apr 2026

Search: “llm”

New release of LLM adds support for reasoning traces, OpenAI Responses, server-side tools, and smarter logging

New VIDEO: From LLM Wikis to LLM Artifacts Shared all my thoughts on why LLM wikis and HTML artifacts are a big deal. Plus, new tools to hel…

LLM-Auction: Generative Auction towards LLM-Native Advertising

Learn how to build LLM Wikis and LLM Artifacts.

LLM 0.32a0 is a major backwards-compatible refactor

UNSEEN: A Cross-Stack LLM Unlearning Defense against AR-LLM Social Engineering Attacks

LLM Artifacts Connected to @karpathy's LLM Knowledge base idea, I've been building out a fun way to generate dynamic artifacts from these kn…

llm-typesafe 0.1a0

AIR-LLM: Broadcasting AI Weights over Radio for Memory-Free Edge LLM Inference via RF Computing

// Your LLM judge disagrees with the experts // LLM Judges can be tricky to build. Here is an interesting showcasing why: There propose a re…

Gary Marcus 又放大招了！ 他直接把 Claude Code 源码泄露后的核心真相点破： ✅ Claude Code 是 LLM 时代以来最大进步 ✅ 但它根本不是纯 LLM，也不是纯深度学习 ✅ 核心文件 print.ts 足足 3167 行，塞满了 if-then …

llm-chat-completions-server 0.1a0

P3-LLM: An Integrated NPU-PIM Accelerator for Edge LLM Inference Using Hybrid Numerical Formats

I released LLM 0.32a0 this morning, a major backwards-compatible refactor of my LLM Python library and CLI tool for working with language mo…

llm-openai-decisions 0.1a0

llm 0.33

LLM-Advisor: An LLM Advisor for Cost-efficient Path Planning across Multiple Terrains

In the era of base LLM scaling (2022-2024), I believed the LLM line of research would reach a capability plateau (as later seen with base LL…

LLM-OSDA: An Optimal-Stopping Dynamic Auction for Native Advertising in Multi-Turn LLM Conversations

llm 0.32rc2

Another fascinating paper on LLM Judges. (bookmark it) It's from Amazon, and they show that if you run panels of LLM judges, averaging their…

Ray Data LLM enables 2x throughput over vLLM’s synchronous LLM engine at production-scale

LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation

LLM-HYPER: Generative CTR Modeling for Cold-Start Ad Personalization via LLM-Based Hypernetworks

Claude Code is not AGI, but it is the single biggest advance in AI since the LLM. But the thing is, Claude Code is NOT a pure LLM. And it’s …

I Distilled an LLM into two 287M encoders (GLiNER + multiple choice) for document extraction, can't match teacher. did i do something wrong?

When Does a Classifier Help an LLM? Classifier-Guided Prompting and Hybrid Classifier-LLM Models for Credit-Default Prediction

WIP: LLM Odyssey: A Game-Based Platform for Teaching LLM Engineering Concepts

FusionFactory: Fusing LLM Capabilities with Multi-LLM Log Data

LLM-ACES: Closed-Loop Discovery of Dynamical Systems with LLM-Guided Adaptive Search

llm spend is starting to get really high... a key part of our LLM gateway is spend visibility and spend control sign up for the private beta…

LLM Wikis + HTML Artifacts are insanely powerful. You should seriously consider this in your workflows. LLM Wikis captures all the important…

LLM-ADAM: A Generalizable LLM Agent Framework for Pre-Print Anomaly Detection in Additive Manufacturing

LLM-Rosetta: A Hub-and-Spoke Intermediate Representation for Cross-Provider LLM API Translation

The largest agentic LLM Inference dataset has arrived! 206B tokens · 12,002 sessions · 1,186,582 LLM requests · 1,213,347 tool calls The tra…

Understanding Issues, Causes and Solutions in Open-Source LLM-based Multi-Agent Systems

LLM next-token prediction is already a probabilistic classifier, so an open LLM can serve a Jev-like interface: discrete options in, fast pr…

llm 0.36

Toward Sustainable Distributed LLM Inference: A Systems Synthesis and Research Agenda for an Energy-, Carbon-, and Cache-Aware llm-d Control Plane

User Perceptions vs. Proxy LLM Judges: Privacy and Helpfulness in LLM Responses to Privacy-Sensitive Scenarios

Incident-Data Robustness Analysis of the OWASP Top 10 for LLM Applications (2026): How a Community-Expert Ranking Holds Up Against a Large-Scale LLM Incident Corpus

llm 0.32.1

llm-gemini 0.33

LLM Agents Factory: Retrieval of Domain-Specific LLM Agents

Your LLM, Your Style: Behavioral Mode Axes for LLM Behavioral Control

Introducing Sakana Namazu: An LLM API with Japanese-vibes! Today we’re rolling out an upgraded version of our LLM, Namazu, now available as …

llm 0.32rc1

🚨Emergency webinar: LLM Wikis and how to give your agent memory LLM Wikis are so hot right now - OpenWiki by @BraceSproul up to nearly 7k G…

Gary Marcus 又放大招了！他直接把 Claude Code 源码泄露后的核心真相点破： ✅ Claude Code 是 LLM 时代以来最大进步 ✅ 但它根本不是纯 LLM，也不是纯深度学习 ✅ 核心文件 print.ts 足足 3167 行，塞满了 if-then …