AIQB
Article system

AI Intelligence Archive

浏览 AIQB 已保存的 6406 stories AI intelligenceArticles，覆盖Models、Products、Industry、Research、教程与观点方法六大分类。

Indexed articles6406
Categories6
Selected stories2

All articles

Section 122 / 161 页 · 每页 40 stories

TutorialsOrdinary
Three Agent Runs Passed. One Missing Handoff Broke the Workflow
My triage agent extracted a refund request and its order reference. The refund specialist said the...
Source: DEV Community
TutorialsOrdinary
Why AI Agents Shouldn’t Calculate Bazi Charts From Memory
A calculation-first MCP server for Four Pillars, True Solar Time, and auditable chart data Large...
Source: DEV Community
ResearchOrdinary
MAPLE: Memory-Augmented Planning with Language and Evolution
Domain practitioners understand their business constraints but may lack operations-research expertise or dedicated support. LLM-based optimization agents translate natural-language requirements into models or solver programs that establish…
Source: arXiv
ResearchOrdinary
Physics-Informed Neural Networks to Infer the Perpendicular Energy Conductivity in the Scrape-Off Layer of Stellarator Devices
In this work, we develop an inverse Physics-Informed Neural Network (PINN) framework to infer the dependence of the scrape-off layer (SOL) perpendicular heat conductivity on plasma density and temperature, $κ_\perp(n,T)$. The method combin…
Source: arXiv
TutorialsOrdinary
Build a Shipment Control Tower with ToolJet MCP
Introduction When you build a shipment control tower with ToolJet MCP, freight operations...
Source: DEV Community
ResearchOrdinary
A Training-Free, Alignment-Free Approach to Corporate Intelligence: Application to SEC Filings
High-dimensional dense text embeddings and large language models face real obstacles in financial-disclosure analysis: context-window limits, hallucination risk, high computational cost, and the arbitrary rotation of vector spaces across i…
Source: arXiv
ResearchOrdinary
Distributed Optimization of Modular Production Systems using Model-based Reinforcement Learning with Inverse Models
This paper presents a novel approach for data-driven self-learning control of highly flexible, modular manufacturing systems. Specifically, we employ a novel framework for model-based reinforcement learning which introduces approximate inv…
Source: arXiv
ResearchOrdinary
Making Alternative Data Work: Context-Augmented LLMs for Financial Forecasting
When forecasting a firm's future financial performance, alternative data - data collected from non-traditional sources such as consumer transactions, web traffic, and prediction markets - can provide timely signals about firms' operating a…
Source: arXiv
ResearchOrdinary
Identifiability of Nonnegative Tensor Decompositions via Positive Scattering
Identifiability of tensor decompositions is often established through linear-algebraic conditions on the factor families. For nonnegative decompositions, however, positivity provides additional information that is not captured by dimension…
Source: arXiv
ResearchOrdinary
A distribution-free certification framework for trustworthy crash-severity prediction
Crash-severity models inform screening, dispatch and site prioritization, yet are deployed without a finite-sample statement of what one prediction means. Off-the-shelf guarantees fail here, because the features that make crash severity di…
Source: arXiv
TutorialsOrdinary
VAX, TCP/IP, and Thirty Years of the Same Trust Problem
A Japanese version of this is on Note. I build RoamSwitch, a network security app for Mac and Linux,...
Source: DEV Community
ResearchOrdinary
A Dataset and Model for Imputing Water Surface Elevation on a Large and Extremely Sparse Spatiotemporal Graph
Continuous monitoring of water surface elevation across river networks is critical for flood forecasting, water resource management, and understanding the global water cycle. Yet, the scarcity of in situ gauges across much of the globe con…
Source: arXiv
ResearchOrdinary
Learn the Solid, Not the File: Canonical Inputs for Neural Networks on CAD Boundary Representations
Boundary representation (B-rep) is the standard format used by modern CAD systems for parametric 3D models. It turns out, the exact same solid can be represented by different B-reps: for example, two engineers using different operations, a…
Source: arXiv
ResearchOrdinary
Enabling Knowledge Graph Understanding at Scale with the EXplore Your Graphs ENgine (EXYGEN)
We present EXYGEN (EXplore Your Graphs ENgine), a framework for knowledge graph (KG) understanding that enables conversational access to KGs at scale. We address two questions in sequence. First, how effectively can LLMs perform text-to-SP…
Source: arXiv
TutorialsOrdinary
I Was Running 3 AI Coding Agents Locally and Had No Idea What They Were Breaking
Like many developers over the past few months, my daily workflow quietly shifted from typing code...
Source: DEV Community
ResearchOrdinary
A Comparative Evaluation of Pre-trained Convolutional Neural Networks for Melanoma Detection
Early diagnosis of melanoma is critical for improving patient survival rates. However, accurately distinguishing melanoma from other skin lesions remains a significant clinical challenge due to the high visual similarity among lesion types…
Source: arXiv
ResearchOrdinary
Complex-Text Robustness Evaluation and Failure Diagnosis for Low-Resource Multilingual Text-to-Speech
Low-resource multilingual text-to-speech (TTS) systems have expanded language coverage, but their robustness under complex text inputs remains insufficiently diagnosed. Existing evaluations mainly focus on naturalness, speaker similarity, …
Source: arXiv
ResearchOrdinary
Characterizing Job Power Elasticity for Power-Flexible AI Training
Large language model (LLM) training is among the fastest-growing sources of electricity demand in modern data centers, and power availability is a primary bottleneck to continued AI infrastructure growth. Making the power consumption of th…
Source: arXiv
ResearchOrdinary
Particle GFlowNets: Rethinking Generative Marginalization Models
Generative Marginalization Models (MaMs) have been recently introduced as efficient neural sampling models for any-order autoregressive modelling of discrete distributions. By learning both the marginal and conditional probabilities of a p…
Source: arXiv
ResearchOrdinary
Prompt Revision as a Source of Cultural Bias in Text-to-Image Systems
Commercial text-to-image systems silently revise user prompts before generating images, a step users typically cannot disable or even see. Yet, existing audits of cultural bias examine only the final images and treat generation as a single…
Source: arXiv · GPT
ResearchOrdinary
Lightweight LiDAR-Based Cone Detection Framework Using Random Forest for Formula Student Driverless
Reliable, low-latency perception is crucial for Formula Student Driverless vehicles, yet many existing pipelines rely on deep learning and multi-sensor fusion, often requiring GPU acceleration. This paper presents a lightweight LiDAR-only …
Source: arXiv
TutorialsOrdinary
Auto memory on 21 projects: 17 empty, and 3 repos learned the same fix separately
Claude Code's auto memory is on by default and writes to a per-repository directory you probably...
Source: DEV Community · Claude
TutorialsOrdinary
n8n Assistant Launches as a Preview AI Workflow Builder for Cloud and Docker Users
n8n has launched n8n Assistant, a preview AI-assisted workflow builder designed to turn a...
Source: DEV Community
TutorialsOrdinary
I ported JPEG AI to Apple silicon—and the first benchmark was mostly startup
A native Core ML JPEG AI encoder/decoder, real y and z activation maps, and why a five-second result did not mean the codec was slow.
Source: DEV Community
TutorialsOrdinary
Agentic Guardrails for LangChain: The Manifest You Didn't Know You Needed
Guardrails, or the lack of them In July 2025, a Replit AI coding agent deleted a...
Source: DEV Community
TutorialsOrdinary
n8n Assistant Adds Credential Approval Controls and Plan-Based AI Credit Usage
n8n has introduced n8n Assistant, a preview chat-based builder that can plan, construct, test, and...
Source: DEV Community
TutorialsOrdinary
Why User Provisioning Matters for Enterprise AI
Offboarding a user is not enough when the credentials they leave behind can still spend money and...
Source: DEV Community
TutorialsOrdinary
Fourteen years of blog posts, seven languages, one laptop: an open-weight model did our hreflang backfill
In May I had 5,892 blog posts spread over seven hosts, the oldest dated November 7, 2011, and not one...
Source: DEV Community
TutorialsOrdinary
What Happens When You Put a Lie Inside the Information an AI is Supposed to Trust?
What a poisoned support article can actually make the agent do Part 10 findings of an experiment:...
Source: DEV Community
TutorialsOrdinary
Adding a remote MCP server to a Next.js app, OAuth and all
Most "add MCP to your app" posts stop at stdio: a local process, a config file, a token you paste in....
Source: DEV Community
TutorialsOrdinary
What the X API actually costs an LLM agent, per tool call
There is no free tier on the X API any more. For new developers the subscription tiers are gone and...
Source: DEV Community
TutorialsOrdinary
We built an AI that presents your deck in the meeting. Here is what broke first.
Capability-level notes from building Hannah, an AI presenter that joins Teams/Meet/Zoom, presents a deck and answers questions from your material.
Source: DEV Community
TutorialsOrdinary
Our MCP server was fine. Cloudflare was returning HTML.
Three days chasing a protocol bug that was not in the protocol. The user agent matrix, the exact block page an agent receives, and the trick that proved the problem was not ours.
Source: DEV Community
PerspectivesOrdinary
On Binary Translation and its Consequences
Source: Chips and Cheese（RSS）
TutorialsOrdinary
The delegation test is whether you can write the check first
Every discussion I see about what to hand off to a coding agent sorts tasks by difficulty. Easy...
Source: DEV Community
TutorialsOrdinary
I built an engineering roadmap that skips the video tutorials
Most developer roadmaps sell a fantasy that looks like this: HTML → CSS → JavaScript → React →...
Source: DEV Community
TutorialsOrdinary
Build an AI Agent (From Scratch)
This review is about Build an AI Agent (From Scratch) by Jungjun Hur and Younghee Song from...
Source: DEV Community
TutorialsOrdinary
nginx will proxy the new HTTP QUERY method. It will never cache one.
RFC 10008 made QUERY explicitly cacheable. I built a QUERY-only API and found nginx forwards it happily and caches it never: four identical QUERY requests hit the backend four times, four POSTs hit it once.
Source: DEV Community
TutorialsOrdinary
The New Attack Surface: AI Agents With Access to APIs, Databases, and Shell Commands
Your agent can read support tickets, query Postgres, call internal APIs, and run shell commands to...
Source: DEV Community
TutorialsOrdinary
What Should an AI Agent Be Allowed to Do Without Asking You?
Your agent notices a failing deployment. It reads the logs, identifies the bad commit, drafts a...
Source: DEV Community