Claude has been running my nanochat experiments since morning. It writes implementations, debugs them with toy examples, writes tests and makes them fail/pass, launches training runs, babysits them by tailing logs and pulling stats from wandb, keeps a running markdown file of
AGENTS
-
LLM Inference Visualizer: Interactive Tool for Message Flow
By
–
LLM Inference Visualizer Made by the LangChain Community Interactive tool visualizing LLM inference through drag-and-drop messages. Uses LangChain's message types to show how context, system prompts, and tool calling workflows shape model outputs in real-time. Watch the
-
Personal LLM-as-a-Judge: Continuous Learning System
By
–
The best early application of continuous learning is your personal LLM-as-a-judge. Imagine an LLM that knows exactly how you code, write emails, what you consider to be 'good' legal document or what is a good design – anything that you normally give feedback to LLMs on is
-
Tinyfish virtualized web browser acts like human for AI agents
By
–
Pay attention to Tinyfish. They have a virtualized web browser that spins up, decomposes the webpage it's sent to see, and can act like a human being—filling in information, getting data, looking at different things, and bringing that back to your AI agents. You're right on; the
-
Waymo car predicts reality, then drives through it
By
–
A Waymo car predicts reality; it predicts where everybody's going to be in about one second. That's called "predicting reality" as it drives along. Then, it drives through the reality that it predicted. It's a funny thing to watch. But yeah, humans are patterns. The founder of
-
Claude Code Discovers Lutron Home Automation System Network
By
–
I was inspired by this so I wanted to see if Claude Code can get into my Lutron home automation system. – it found my Lutron controllers on the local wifi network
– checked for open ports, connected, got some metadata and identified the devices and their firmware
– searched the -
Builders using Anthropic Claude are the future, not emotional support
By
–
Meanwhile all the smartest people I follow are posting about things they are building with Anthropic Claude. The builders are the future. Those who hang onto models for emotional support are not. I'd rather help the builders figure things out. And I know that makes me tone
-
OpenAgent Framework: AI Agents for Web3 with Verifiable Compute
By
–
OpenAgent Framework Made by the LangChain Community OpenAgent is an AI agent framework for Web3 with verifiable compute—enabling cryptographic proof of execution for DeFAI and DeSci applications requiring trust and precision. GitHub: https://
github.com/webisopen/Open
Agent
… Docs: -
MiniMax M2.1: Agent-Optimized AI Model for Coding and Planning
By
–
Now on Poe: MiniMax M2.1 An agent-optimized model built for coding, tool use, and long-horizon planning served via @novita_labs (1/2)
-
Critique of agentic abstraction layers in AI application development
By
–
Non jamais. Je dev tout. Les couche d’abstraction agentique c’est un enfer. J’ai vécu la création et la monté de la hype de langchain et dès le début j’ai voulu en être loin, parce que j’ai connu jusqu’où la pénétration d’une lib à la mode dans une stack peut te flinguer ta dette