All Articles

143218 articles · Page 309 of 7161
Machine Learning Algorithms & Natural Language Processing
Machine Learning Algorithms & Natural Language Processing
May 19, 2026 · Artificial Intelligence

From P(y|x) to P(y): Reinforcement Learning in Pre‑train Space Unlocks Endogenous Reasoning

The paper introduces PreRL, which removes the input condition to directly optimize the reasoning trajectory (P(y)) of large language models, and combines it with standard RL in Dual Space RL (DSRL), achieving consistent gains on math and out‑of‑distribution benchmarks, faster training, and richer reasoning behaviors.

DSRLMath BenchmarksPreRL
0 likes · 11 min read
From P(y|x) to P(y): Reinforcement Learning in Pre‑train Space Unlocks Endogenous Reasoning
AI Agent Research Hub
AI Agent Research Hub
May 19, 2026 · Artificial Intelligence

Physics‑Informed Neural Networks for Navier‑Stokes Flow Parameter Identification

This tutorial demonstrates how continuous physics‑informed neural networks (PINNs) combined with stream‑function parameterization and nested forward‑mode automatic differentiation (JVP) can accurately identify the convection and viscosity coefficients of a two‑dimensional Navier‑Stokes cylinder‑wake problem from sparse velocity observations, achieving sub‑0.2% error for the convection term and robust performance even with 1% measurement noise, all within a few minutes on a single RTX 4090 GPU.

Deep LearningJAXNavier-Stokes
0 likes · 28 min read
Physics‑Informed Neural Networks for Navier‑Stokes Flow Parameter Identification
Deepin Linux
Deepin Linux
May 19, 2026 · Fundamentals

Master the Linux fasync Mechanism and Understand Signal‑Driven Asynchronous Notification

This article explains the Linux kernel fasync mechanism, compares it with other I/O models, details the underlying data structures and key functions, and provides step‑by‑step driver and user‑space code examples for implementing signal‑driven asynchronous notifications in embedded and Linux driver development.

Linux kernelSIGIOasynchronous notification
0 likes · 35 min read
Master the Linux fasync Mechanism and Understand Signal‑Driven Asynchronous Notification
Linyb Geek Road
Linyb Geek Road
May 19, 2026 · Artificial Intelligence

Five Best Design Patterns for AI Agent Skills

This article explains five practical design patterns—tool wrapper, generator, reviewer, inversion, and pipeline—for structuring AI agent SKILL.md files, showing when to use each, how they work internally, and how they can be combined for robust, maintainable agent behavior.

AI agentsLLMPrompt Engineering
0 likes · 19 min read
Five Best Design Patterns for AI Agent Skills
Architecture Breakthrough
Architecture Breakthrough
May 19, 2026 · Industry Insights

Deposit Reserves vs. Provision Funds: A Simple Guide to What Banks Can Freely Use

The article explains how commercial banks must set aside deposit reserves and provision funds—mandatory reserves locked with the central bank and daily liquidity kept for operations—and how gold‑backed deposit products add complexity, illustrating why only the remaining funds are truly free for the bank to deploy.

bankingfinancial regulationgold-backed deposits
0 likes · 7 min read
Deposit Reserves vs. Provision Funds: A Simple Guide to What Banks Can Freely Use
AI Architecture Hub
AI Architecture Hub
May 19, 2026 · Artificial Intelligence

Agent Memory: From Theory to Practical Implementation

The article explains how AI agents can acquire long‑term memory by combining three functions—coherence, context, and learning—with four memory types, describes the full retrieval‑store loop, and provides a step‑by‑step Python implementation using OpenAI embeddings, ChromaDB, and forgetting strategies.

AI agentsChromaDBPython
0 likes · 17 min read
Agent Memory: From Theory to Practical Implementation
AI Engineer Programming
AI Engineer Programming
May 18, 2026 · Artificial Intelligence

Designing an Agent Gateway: Bridging Business Logic and Protocol Infrastructure

The article analyzes why traditional API gateways cannot meet the needs of stateful Agentic workflows and proposes a dedicated Agent gateway that handles access control, cross‑service execution tracing, and pre‑LLM security enforcement while addressing connection overhead, session fan‑out, and observability challenges.

A2AAI securityAgent Gateway
0 likes · 14 min read
Designing an Agent Gateway: Bridging Business Logic and Protocol Infrastructure
Java Architect Essentials
Java Architect Essentials
May 18, 2026 · Backend Development

Meet Reqable: A Free, Cross‑Platform Postman Alternative with Superior Performance

Reqable is a free, cross‑platform API testing tool built with Flutter and C++ that offers instant startup, low memory usage, offline storage, HTTP/2‑3 support, data migration from other tools, packet‑capture debugging, and an active open‑source community, positioning it as a high‑performance replacement for Postman.

C++FlutterPostman alternative
0 likes · 7 min read
Meet Reqable: A Free, Cross‑Platform Postman Alternative with Superior Performance
Machine Heart
Machine Heart
May 18, 2026 · Artificial Intelligence

ICML 2026: From Single‑Threaded Thinking to Native Parallel Reasoning in Agents

The paper introduces Native Parallel Reasoner (NPR), a framework that lets language agents generate and maintain multiple reasoning paths using a three‑stage self‑distillation and parallel reinforcement‑learning training paradigm, achieving up to 4.6× speedup and significant accuracy gains across eight reasoning benchmarks.

AI reasoningNative Parallel ReasonerSelf-Distillation
0 likes · 18 min read
ICML 2026: From Single‑Threaded Thinking to Native Parallel Reasoning in Agents
Machine Heart
Machine Heart
May 18, 2026 · Artificial Intelligence

Composer 2.5 Delivers Opus‑level Performance at One‑Tenth the Cost

Composer 2.5, Cursor’s latest LLM, matches Claude Opus 4.7‑level capabilities while costing roughly one‑tenth as much, thanks to larger training scale, precise text‑feedback reinforcement learning, 25× more synthetic tasks, and a new Muon‑HSDP optimizer that boosts efficiency up to ten‑fold.

Composer 2.5LLMMuon Optimizer
0 likes · 9 min read
Composer 2.5 Delivers Opus‑level Performance at One‑Tenth the Cost
BirdNest Tech Talk
BirdNest Tech Talk
May 18, 2026 · Artificial Intelligence

Taming AI Coding Agents: A Powerful Development Workflow with Engineering Discipline

The article introduces Matt Pocock's open‑source "skills" collection for AI coding agents, shows how it embeds traditional engineering practices such as alignment, domain modeling, TDD, and architecture governance into reusable command sets, and walks through a complete partial‑refund feature implementation using these skills.

AI Coding AgentsArchitecture GovernancePrompt Engineering
0 likes · 22 min read
Taming AI Coding Agents: A Powerful Development Workflow with Engineering Discipline
Code of Duty
Code of Duty
May 18, 2026 · Artificial Intelligence

Codex vs Cursor vs Claude Code: How to Choose the Right AI Coding Tool

This article compares three leading AI coding assistants—Codex, Cursor, and Claude Code—by examining their workflows, strengths, limitations, and ideal user scenarios, and provides practical guidance on selecting the tool that best fits personal, team, or enterprise development needs.

AI codingClaude CodeCodex
0 likes · 14 min read
Codex vs Cursor vs Claude Code: How to Choose the Right AI Coding Tool
dbaplus Community
dbaplus Community
May 18, 2026 · Information Security

One Bash Script, One Weekend: How AI Uncovered a 23‑Year‑Old Linux Kernel Flaw

A simple Bash script run over a weekend by researcher Nicholas Carlini leveraged Claude Opus 4.6 to discover a critical NFSv4 vulnerability that had persisted in Linux kernels since March 2003, prompting Linus Torvalds to announce AI‑driven security as a new normal in the Linux 7.0 release.

AI-assisted Vulnerability DetectionLinuxLinux 7.0
0 likes · 19 min read
One Bash Script, One Weekend: How AI Uncovered a 23‑Year‑Old Linux Kernel Flaw
SuanNi
SuanNi
May 18, 2026 · Artificial Intelligence

How Kimi WebBridge Lets AI Control Your Browser Like a Human

Kimi WebBridge is a browser extension that bridges local AI agents and Chrome/Edge, enabling the AI to act with the user's login state, cookies, and account to click, scroll, fill forms, and extract data securely on the local machine, while remaining non‑intrusive and supporting custom CLI tools.

AI AgentCLIChrome DevTools Protocol
0 likes · 11 min read
How Kimi WebBridge Lets AI Control Your Browser Like a Human