Eclipse LMOS
We Cannot Throw Away Ten Years of Experience Just to “Build a New Team and Replace the Entire Stack” --- Introduction The Eclipse Foundation recently introduced the Agent Definition Language (ADL) into its open-source Eclipse LMOS platform — a structured, model-agnostic description method to define AI behavior without writing code. ADL
Meituan AI
Meituan’s “Food Delivery Speed” Approach to AI Models Meituan appears to be embracing a “fast and stable” AI development mantra — rapidly releasing new models while maintaining high performance. Over the past two months, multiple models have been launched, and the momentum continues. --- Introducing LongCat‑Flash‑Omni The newest
Claude Code
# Mastering Claude Code: Full Feature Guide & Best Practices This guide explores **how to use each feature of Claude Code**, **when to use them**, and **ways to maximize their value** — distilled from expert insights shared by software engineer & security engineer **Shrivu Shankar**, with additional endorsements from practitioners such as
ReAct paradigm
Introduction In developing an intelligent solution system, a key challenge emerged: how to enable AI to maintain strong reasoning abilities while executing actions in complex tasks. Traditional AI systems typically rely solely on model reasoning with static training data or fixed workflows — both lacking dynamic decision-making capability. The ReAct (Reasoning
AI models
The Third Scaling Paradigm in AI Emu3.5 Ushers in a Native Multimodal World New Intelligence Report Editor: Peach Sleepy --- Executive Summary The third scaling paradigm in AI is here — Emu3.5. With 34 billion parameters, trained on the equivalent of 790 years of long-form video, this native multimodal
AI assistant
Z Highlights Image source: The Interaction Company of California, Inc. * A bold new AI assistant called Poke has been created by a 10-person team, breaking away from the traditional “people‑pleasing” AI persona. To join, users must first convince an AI gatekeeper and negotiate the subscription price—almost like striking
AI robotics
Launch of 1X Technologies Home Humanoid Robot NEO On October 28, 1X Technologies (formerly Halodi Robotics) officially began sales of its home humanoid robot — NEO. Pricing & Availability * Early-bird price: USD 20,000 (≈ RMB 141,978) per unit * Monthly rental plan: USD 499 (≈ RMB 3,542) --- Hardware Highlights NEO
JavaScript
🐞 Common Bug Pattern in API Calls Many developers have unintentionally written bugs like this (not exactly like the image 👇): Typical `try–catch` Example try { const res = await api.getUser() console.log('✅ User info', res) } catch (err) { console.error('❌ Request failed', err) } At first glance, this code
Claude Code
Claude Code Excels at Debugging Low-level Cryptography Original report by Filippo Valsorda (via Hacker News) Go cryptography author Filippo Valsorda has shared highly encouraging results using Claude Code for the implementation and debugging of new cryptographic algorithms. Key Highlights * Claude successfully identified and resolved a complex low-level bug in newly
AI course
# Datawhale Course **Course:** AI Research Foundations **Compiled by:** Datawhale --- ## Learn Artificial Intelligence from Top Experts Google DeepMind, in collaboration with **University College London (UCL)**, has launched a free course — **AI Research Foundations**. This course is designed to help learners: - Gain a **deep understanding of Transformers**. - Develop **hands-on
Infrastructure-as-Code
2025-11-02 10:15 — Beijing Infrastructure tooling company Platform Engineering Labs has launched an open-source Infrastructure-as-Code (IaC) platform called formae, aiming to address what it sees as the fundamental limitations of existing IaC solutions. --- 🚀 Launch Overview On October 22, 2025, Platform Engineering Labs positioned formae as the first major IaC
real-time AI
# Large Model Intelligence｜Sharing ## Real-Time VLA Models: How Fast Can They Go? **VLA (Visual-Language-Action)** models are often thought of as slow, with inference times in the tens or hundreds of milliseconds. However, in their paper *RT-VLA (Real-time VLA)*, researchers from embodied intelligence company **Dexmal** (co-founded by Haoqiang Fan and others)