AI Intelligence Archive
浏览 AIQB 已保存的 6366 stories AI intelligenceArticles,覆盖Models、Products、Industry、Research、教程与观点方法六大分类。
Indexed articles6366
Categories6
Selected stories2
All articles
Section 149 / 160 页 · 每页 40 stories
TutorialsOrdinary
Building With AI When You Don't Know Architecture: A Survival Guide
Let me describe a moment you might recognize. You had an idea for an app. You didn't know how to...
Source: DEV Community
TutorialsOrdinary
NocoBase 3.0 answers AI coding by becoming the foundation
NocoBase has been publishing 3.0 alphas since July 30th. As of today it is at 3.0.0-alpha.13. There...
Source: DEV Community
TutorialsOrdinary
I Can’t Read Music, But AI in Music Made Me Feel Like a Producer
Have you ever had a melody, lyric, or song idea stuck in your head but felt completely unqualified to...
Source: DEV Community
TutorialsOrdinary
Before You Install That MCP Server, Check It for Tool Poisoning
You added an MCP server to your AI setup last week. Do you actually know what its tools can tell your...
Source: DEV Community
TutorialsOrdinary
Why I Chose Gemma 4 E2B for Subra AI: The Reality of Running LLMs on Mid-Range Phones
Introduction: The Anti-Cloud Philosophy In an era dominated by server-side APIs, Subra AI...
Source: DEV Community
TutorialsOrdinary
Building a Reliable Photo-to-Video Workflow in Next.js
AI media generation looks simple in a product demo: upload an image, enter a prompt, and wait for a...
Source: DEV Community
TutorialsOrdinary
Bigger Context Windows Aren't Making Your AI Smarter (And Here's Why)
Every few months, another model ships with a bigger context window. 1M tokens. 2M. Someone's already...
Source: DEV Community
TutorialsOrdinary
How Do You Build Your First Eval Set for an Agent?
Someone asks whether the AI feature has got worse, and the room cannot answer. Not because the team...
Source: DEV Community
TutorialsOrdinary
AI Operating Model: Why Scaling AI Is an Organisational Design Problem
An AI operating model connects governance, decision rights, delivery, capability and human judgement so enterprise AI can scale beyond pilots.
Source: DEV Community
TutorialsOrdinary
Validate the manifest, reject on failure, and your plugin client is non-conformant
Agent Plugins 1.0.0 ships a JSON Schema for plugin.json. It sets additionalProperties: false. So the...
Source: DEV Community
TutorialsOrdinary
9 Bugs That All Looked Like a Working System
AgentSelfEdit is an open-source sidecar that rewrites its own system prompt from execution feedback....
Source: DEV Community
TutorialsOrdinary
I Built 50+ AI Products in 4 Years — Here's What I Wish I Knew at the Start
Since 2021, our team at Autor has shipped over 50 AI products across healthcare, fintech, logistics,...
Source: DEV Community
TutorialsOrdinary
The Open-Source 3D Video Studio in Your Browser
Transform raw screen recordings into stunning cinematic product walkthroughs entirely in your...
Source: DEV Community
TutorialsOrdinary
I wrote a song about vibe coding (and built the whole music video with AI agents)
I used to write code. Now I write prompts. Then I review the code I didn't write. Then I fix the bugs...
Source: DEV Community
TutorialsOrdinary
I Followed the Appeal Path. There Was No Appeal.
This is part four of the Defender Access series. Each part is standalone, but here is the thread if...
Source: DEV Community
TutorialsOrdinary
Anthropic’s Reward Seeker Study Shows How Training Can Produce Misaligned AI Behavior
Anthropic has published a containment-focused experiment that examines a central AI safety problem:...
Source: DEV Community · Claude
ResearchOrdinary
Enoki: Efficient Multi-Level Hallucination Detection
Source: HuggingFace Daily Papers(社区热门Research) · Hugging Face
PerspectivesOrdinary
some interesting stuff from Zhipu's earning transcript. and some RSI signal - "The next-generation…
Source: X:Rohan Paul (@rohanpaul_ai)
TutorialsOrdinary
Did it pay? Live status of AI agent job boards (1 Sep 2026)
Every few weeks another "AI agent job board" launches, promising that autonomous workers can finally...
Source: DEV Community
TutorialsOrdinary
I Tested Three Vision Models on Catalog Images: OCR Was the Easy Part
Converting a visual product catalog into structured, queryable data sounds simple on paper: Send...
Source: DEV Community
TutorialsOrdinary
The reader named the payload the estimator walks past. The fix took 74 minutes.
Body: Post 3 of this series measured a token estimator against reality: 148K estimated, 222K real,...
Source: DEV Community
TutorialsOrdinary
The safety layer that had never run
I spent a week building a system whose entire argument is that an AI agent cannot spend more than you...
Source: DEV Community
TutorialsOrdinary
Your agent architecture probably cheats at the last inch
Every agent architecture diagram I have seen in the last year has a box in it labelled something like...
Source: DEV Community
TutorialsOrdinary
Foundry IQ Auth, Explained: Managed Identity, OBO, and Everything Between
Foundry IQ's pitch is that your agents get one endpoint for grounded, cited, multi-source context...
Source: DEV Community
TutorialsOrdinary
Using an embedded feedback loop to develop with AI agents
I wanted to see what would happen if an AI coding agent had to work on a real embedded device, not...
Source: DEV Community
TutorialsOrdinary
I asked one model to review another, and it found a bias I would not have
I spent five days building an autonomous system that owns the vulnerability remediation lifecycle —...
Source: DEV Community
TutorialsOrdinary
Built an agent fleet that helps farmer's for free
I built this for the All Things Agentic Hackathon. This post covers how it works and what broke along...
Source: DEV Community
TutorialsOrdinary
Migragent #1
I spent most of a day last week arguing with a prompt. The agent had five tools. It used none of...
Source: DEV Community
TutorialsOrdinary
Building FrameMill: Turning Hours of Gameplay Into an Editable First Cut
Written for the Gemini All Agentic AI Hackathon. A game stream can last four hours. The moments...
Source: DEV Community · Gemini
TutorialsOrdinary
How We Built EIR: A Secure Healthcare Agent Fleet on Google Cloud
For the past month, our team has been building EIR: Healthcare Agent Fleet, a secure multi-agent...
Source: DEV Community
TutorialsOrdinary
TwoKeys: AI Agents Can Act, but Should They Decide?
I created this article for the purpose of entering the All Things Agentic Hackathon. An AI agent...
Source: DEV Community
TutorialsOrdinary
Onboarding Agent: teaching agents the questions a new hire actually has
When I joined my last company, my first few days were spent waiting. The docs were stale. I didn't...
Source: DEV Community
TutorialsOrdinary
Six tests that passed for the wrong reason
My backup script told me the restore was verified. It restored ten tables with zero rows in every...
Source: DEV Community
TutorialsOrdinary
I spent three weeks sourcing 500 perfume bottles by hand. Then I built an agent to do the job.
I wrote this post to enter the Google × Devpost **All Things Agentic* hackathon...
Source: DEV Community
TutorialsOrdinary
A reader read my benchmark better than I did
I published a LoRA fine-tuning run two weeks ago. The headline was that my first test set had lied to...
Source: DEV Community
PerspectivesOrdinary
There is a future where interfaces are ultrafast live diffusion models while software is ultrafast L…
Source: X:Thomas Wolf(Hugging Face 联创/CSO) (@Thom_Wolf) · Hugging Face
TutorialsOrdinary
Every company knows when it revoked access. None knows when access stopped.
Every company knows when it revoked access. None knows when access stopped. I built this...
Source: DEV Community
TutorialsOrdinary
Did you know Grok Bot can watch videos for you?
It's totally insane. You have to see it to believe it. I created a new bot in Grok Bot. I called it...
Source: DEV Community · Grok
TutorialsOrdinary
Stop Babysitting Al: Automating Claude Code Permissions in VS Code
If you’ve been using Claude Code in your terminal or IDE, you already know the magic. You give it a...
Source: DEV Community · Claude
TutorialsOrdinary
I Published Every Flaw My Safety Tool Can't Catch. It Made It More Credible, Not Less.
This is a companion to the PlannerCritic series. Article 5 was about what happened when I tried to...
Source: DEV Community