AI Intelligence Archive
浏览 AIQB 已保存的 6353 stories AI intelligenceArticles,覆盖Models、Products、Industry、Research、教程与观点方法六大分类。
Indexed articles6353
Categories6
Selected stories2
All articles
Section 7 / 159 页 · 每页 40 stories
TutorialsOrdinary
the model that doesn't write: an intro to decision models
decision models! new category, showed up on the hub about three weeks ago, and the name is...
Source: DEV Community
TutorialsOrdinary
Your AI Coding Agent Just Built an App. Would You Trust It With Production Data?
AI can build a working application faster than ever. Give an AI coding agent a prompt, and it might...
Source: DEV Community
TutorialsOrdinary
Side Hustle: 6 DevOps Project Ideas Someone Would Actually Pay For (Hacktoberfest DEV Challenge, Week 2)
The theme for Week 2 of the Hacktoberfest DEV Challenge is out: Side Hustle. Build something with...
Source: DEV Community
TutorialsOrdinary
From $0 to my first dev job in 6 months — no CS degree
Six months ago I had $0 in the bank earmarked for this, no computer science degree, and a browser tab...
Source: DEV Community
TutorialsOrdinary
Altair-Next Gen Aims to Bring AI-Powered Satellite Analytics Closer to Real Time
Mistral AI has joined a consortium led by Marlan Space and Loft Orbital to develop Altair-Next Gen, a...
Source: DEV Community · Mistral
TutorialsOrdinary
A local-first AI triage desk: sorting a one-person trade's jobs with Gemma 3
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle The...
Source: DEV Community
TutorialsOrdinary
Udhaar Voice: a credit ledger you fill by talking, built for shopkeepers, running with no internet
This is my submission for the Hacktoberfest Open-Source AI Challenge: Week 2, theme: Side Hustle. ...
Source: DEV Community
TutorialsOrdinary
Cut AI agent token costs with decision models for tool selection
Give an AI agent a real toolset (25, 40, more) and every call pays for it. The agent reads every tool...
Source: DEV Community
TutorialsOrdinary
How We Built a Shared Markdown Board for AI Agents (and Made Checklists Tick Themselves)
A board of markdown docs every agent workspace shares: how checklist items follow task status, how versions stop agents overwriting each other, and why there's no search.
Source: DEV Community
TutorialsOrdinary
I Bridged My Real Logged-In Browser to Chrome's New WebMCP API
I Bridged My Real Logged-In Browser to Chrome's New WebMCP API Chrome's WebMCP proposal...
Source: DEV Community
TutorialsOrdinary
SkillJacking Is Real. I Built the Pinning Layer Skills Were Missing.
SkillJacking Is Real. I Built the Pinning Layer Skills Were Missing. Agents install skills...
Source: DEV Community
TutorialsOrdinary
1 in 5 AI-Suggested Packages Doesn't Exist — I Built a Scanner for That
1 in 5 AI-Suggested Packages Doesn't Exist — I Built a Scanner for That You ask an AI...
Source: DEV Community
TutorialsOrdinary
Your Auth Check Passed. The Agent Still Did Something Nobody Asked For
Authentication answers who. Authorization answers what they're allowed to do. Neither one answers...
Source: DEV Community
TutorialsOrdinary
People Are Vibe-Coding Clones of Every Paid App. What Actually Survives?
Earlier this month, a developer in Atlanta got fed up with Adobe's cancellation fees. So he used...
Source: DEV Community
TutorialsOrdinary
research-ledger: a skill that helps one person and several AI models not fool themselves
I am not a professional researcher. I work in IT support, and in the evenings I explore ideas with...
Source: DEV Community
TutorialsOrdinary
Best Enterprise AI Gateways
TL;DR An enterprise AI gateway sits between your applications (and, increasingly, your...
Source: DEV Community
TutorialsOrdinary
One AGENTS.md to rule Claude Code, Cursor and Codex
If you use more than one AI coding agent, you've probably ended up with three instruction files: a...
Source: DEV Community · Claude / Cursor
TutorialsOrdinary
I review NDAs for classmates, so I built a contract-risk scanner that never lets the contract leave your laptop
It usually starts with a message at 11pm: "学长,帮我看看这个合同能签吗?" — "can you take a quick look at this...
Source: DEV Community
TutorialsOrdinary
Designing a prompt builder for a text-to-music model: 500 characters, 4 instruments, and a lot of restraint
A text-to-music API gives you one string. Users give you 'make me a sad song'. Here's how we built a structured prompt builder that fits a 500-character budget — and why we cap instruments at four.
Source: DEV Community
TutorialsOrdinary
We audited our own agent's ledger: 10% of it was one test that never fails
We audited our own agent's ledger: 10% of it was one test that never fails We run an...
Source: DEV Community
TutorialsOrdinary
Don't Try This at Home: What Happened When I Sent Kiro to Work and Went Gardening
There is a special kind of confidence that comes from an AI development environment that just works....
Source: DEV Community
TutorialsOrdinary
# 🛡️ DecisionShield: Building an AI That Checks Decision Readiness Before Recommending a Choice
ai #gemma #opensource #hackathon Don't just ask AI what to choose. Ask AI whether you have...
Source: DEV Community
TutorialsOrdinary
LocalLens: private document Q&A that runs 100% on your machine
LocalLens: private document Q&A that runs 100% on your machine My entry for the...
Source: DEV Community
TutorialsOrdinary
I Fixed Microsoft's BitNet C++ Kernels: How to Run 1-Bit LLMs on Pure CPU Without Compiling
Earlier this year, Microsoft Research published the BitNet b1.58 paper, demonstrating that 1-bit...
Source: DEV Community
TutorialsOrdinary
Only MRDRs in the Repo
Background To talk about MRDRs, we first need to take about MADRs, which are...
Source: DEV Community
TutorialsOrdinary
Building a local MCP server inside a Rust desktop app
How we embedded an MCP server in AssetHoard (Tauri, Rust) so Claude Code, Cursor and friends can search a game asset library, and how we locked it down.
Source: DEV Community · Claude / Cursor
TutorialsOrdinary
Reasoning depth vs latency vs cost
Reasoning Depth vs Latency vs Cost – An Escalation‑Based Design Guide Balancing model...
Source: DEV Community
TutorialsOrdinary
KadaCard: WhatsApp listings from a product photo, scored offline with open-weight CLIP
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community
TutorialsOrdinary
Text and Images in One Embedding Space on a CPU: What I Measured Building a Semantic grep
When I look for an old note or a screenshot, I often remember what it was about but not a single word...
Source: DEV Community
TutorialsOrdinary
How Engineers Should Learn a New Technology in the AI Era
A four-layer model for learning any new technology, and how AI coding changes where to spend your time.
Source: DEV Community
TutorialsOrdinary
Avoid These 4 Claude Code Context Antipatterns
Four ways to quietly pollute your Claude Code context, and how to fix each one with /clear, /rewind, subagents, and a lean CLAUDE.md.
Source: DEV Community · Claude
TutorialsOrdinary
One MCP Server for Six AWS Inference Backends: Bedrock, SageMaker, GPUs, Inferentia and Trainium
A step by step look at the MCP server that runs a six-backend Gemma 4 demo on AWS: one Python file over the demo's own code, eight tools marked read-only, write or destructive, SSM Run Command instead of open ports, and an agent that count…
Source: DEV Community
TutorialsOrdinary
Why a Lock‑Free Ring Buffer Beats Mutex Queues in a 200 kRPS Rust Service
In a telemetry ingest service we were hitting 200 k requests per second on a single 8‑core box. The...
Source: DEV Community
TutorialsOrdinary
RateCon Radar: Gemma reads a trucker's contract in a browser tab, and the contract never leaves the laptop
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle I built this...
Source: DEV Community
TutorialsOrdinary
Anthropic Says Its Defenses Are Reducing Claude Distillation Attack Effectiveness
Anthropic says it has made meaningful progress in reducing the effectiveness of illicit distillation...
Source: DEV Community · Claude
TutorialsOrdinary
Your AI escalated to a human — and the human is now asking the customer to repeat everything
Here's a scene from a deployment review last quarter. The AI agent did its job: a customer asked...
Source: DEV Community
TutorialsOrdinary
Your Agent Forgets Nothing — That's the Problem. End Sessions With a Handoff Note
Long sessions with a coding agent often follow a familiar shape. The first hour is sharp. A few hours...
Source: DEV Community
TutorialsOrdinary
Can a local LLM replace Claude Code? The benchmark everyone quotes is the wrong one.
Every "7 local models that replace Claude Code" list opens the same way: a table of SWE-bench scores,...
Source: DEV Community · Claude
TutorialsOrdinary
The Industrial Revolution of Software Is Here
The Industrial Revolution changed much more than how goods were manufactured. It transformed how...
Source: DEV Community
PerspectivesOrdinary
https://models.dev
https://models.dev
Source: X:opencode (@opencode)