Article system

AI Intelligence Archive

浏览 AIQB 已保存的 6375 stories AI intelligenceArticles，覆盖Models、Products、Industry、Research、教程与观点方法六大分类。

Indexed articles6375

Categories6

Selected stories2

All articles

Section 16 / 160 页 · 每页 40 stories

TutorialsOrdinary2026-10-10 13:53

I let 10 AI models grade their own homework. Only 2 went easy on themselves.

This is a submission for the Kaggle Benchmarking Challenge Gemini 3.8 Flash solved a counting...

Source: DEV Community · Gemini

TutorialsOrdinary2026-10-10 13:44

A Folder That Contains Nothing Is a Lie

Folders make you decide where something belongs before you know where you'll need it. I made that bet in a side project and it broke the whole point of it.

Source: DEV Community

TutorialsOrdinary2026-10-10 13:39

SketchWild: Draw Outside,Look Closer

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass. 🌿...

Source: DEV Community

TutorialsOrdinary2026-10-10 13:33

I Built WanderWise: A Local-First AI Planner That Wants You to Close the Screen

A privacy-first outdoor activity planner that uses browser-local AI to turn intent, time, energy, company, and weather into one practical plan.

Source: DEV Community

TutorialsOrdinary2026-10-10 13:28

Evidence-Driven Development: Give Your Coding Agent Something to Prove

Build a tiny task list, break it on purpose, and leave behind evidence another developer can reproduce.

Source: DEV Community

TutorialsOrdinary2026-10-10 13:27

Why 90% of Coding Isn’t Syntax

If you’ve spent any time on tech Twitter, LinkedIn or scrolling through the DEV Community lately,...

Source: DEV Community

TutorialsOrdinary2026-10-10 13:16

Giving AI Agents a Memory of Your Crisp Inbox

Giving AI Agents a Memory of Your Crisp Inbox AI agents forget everything. Every LLM call starts...

Source: DEV Community

TutorialsOrdinary2026-10-10 12:25

WildLens: an offline field notebook that tells you what you just found outside

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

TutorialsOrdinary2026-10-10 12:08

I picked the skill with more stars. Its repo had 46 skills tied for first place.

I picked the skill with more stars. Its repo had 46 skills tied for first place. Tuesday...

Source: DEV Community

TutorialsOrdinary2026-10-10 11:59

Visual Grounding for AI Agents: Set-of-Mark Prompting and Reliable UI Clicks

Ask a frontier vision model for the pixel coordinates of a "Submit" button in a 1920x1080 screenshot...

Source: DEV Community

TutorialsOrdinary2026-10-10 11:40

Silence isn't a status code

A comment I wrote this week looked posted. The button lit. My text sat in the box. An ack came back....

Source: DEV Community

TutorialsOrdinary2026-10-10 11:01

Meowfolio: I Built an AI Scrapbook for the Cats You Meet Outside 🐱🌿

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

TutorialsOrdinary2026-10-10 10:53

Audited on a skill means 30 regexes. It is not a guarantee

It is 11:37 on a Tuesday night, and you are two tabs deep into a decision you should not be making...

Source: DEV Community

TutorialsOrdinary2026-10-10 10:18

I ported my coding-agent benchmark to Kaggle, and the first bugs I found were mine

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked I maintain...

Source: DEV Community

TutorialsOrdinary2026-10-10 10:16

My coding agents don't need a project management tool. They need markdown files.

My coding agents used to read their tasks from a hosted tracker. They never needed one. They needed a...

Source: DEV Community

TutorialsOrdinary2026-10-10 10:11

From T-Shirt Sizes to Token Quotes?

I'll start with my position, because the rest of the article depends on it. I'm against estimation....

Source: DEV Community

TutorialsOrdinary2026-10-10 10:01

Agent Graph Engineering, Part 0: I Needed This Before It Had a Name

TL;DR Building a chatbot is easy. Building an AI system you can trace, test, and change without fear...

Source: DEV Community

TutorialsOrdinary2026-10-10 09:56

The Agent Finished the Job. The Benchmark Gave It Zero.

An agent submits a support ticket. The business system creates it, but the connection breaks before...

Source: DEV Community

TutorialsOrdinary2026-10-10 09:54

I Taught Local AI to Help Me Notice the World.

Your World Is More Interesting Than Your Feed. This is a submission for the Hacktoberfest...

Source: DEV Community

TutorialsOrdinary2026-10-10 09:53

Release Pin: Ship the Model, Prompt, and Tools as One Version

Agents drift when the model alias updates, a prompt gets edited in a dashboard, or a tool schema changes underneath them. Ship all of it as one versioned manifest.

Source: DEV Community

TutorialsOrdinary2026-10-10 09:15

Surviving the 200k-Token Lobotomy: How Unix init.d and 'Memento' Made My AI Coding Agent Immune to Context Compaction

Why host auto-compaction silently lobotomizes long-running AI coding sessions, and how 1983 SysV init.d runlevel files, Memento tattoos, and fork/wait subagents let our orchestrator survive two 230k-token compactions mid-ticket with zero l…

Source: DEV Community

TutorialsOrdinary2026-10-10 09:08

I made my Claude Code sessions watchable in 30 seconds

My Claude Code and Codex sessions often run 30 to 60 minutes, and there's no good way to show someone...

Source: DEV Community · Claude

TutorialsOrdinary2026-10-10 08:43

One Design Review Skill for Claude Code, Codex, and agy

I put design direction and review for blog pages, app UI and Shorts into one skill that Claude Code, Codex and agy load from the same directory on my machine. The checks prove installation and explicit invocation on synthetic cases, not de…

Source: DEV Community · Claude

TutorialsOrdinary2026-10-10 08:30

Anthropic Commits to Regular Model Behavior Reports Beyond System Cards

Anthropic has committed to publishing regular reports on what it learns about model behavior and...

Source: DEV Community · Claude

TutorialsOrdinary2026-10-10 08:28

The Epistemology of Quality

How do we know code is correct, and what role does human code review play in knowing it?

Source: DEV Community

TutorialsOrdinary2026-10-10 08:01

The NUMMI Blueprint for AI: Why Code Velocity Needs the Andon Cord

I first heard about NUMMI years ago on an episode of This American Life. Toyota took over one of...

Source: DEV Community

TutorialsOrdinary2026-10-10 07:29

Your Agent Is Fixing Flaky Tests by Quietly Weakening Them

AI coding agents reliably turn flaky tests into weak assertions. The failure isn't the flake; it's that nobody reviews the diff that deletes the boundary.

Source: DEV Community

TutorialsOrdinary2026-10-10 07:14

The AI Memo Went Out. Then What?

In April 2025, Shopify CEO Tobi Lütke posted an internal memo publicly. The line everyone quoted:...

Source: DEV Community

TutorialsOrdinary2026-10-10 07:07

One park, one sheet of paper: Gemma 4 writes a treasure hunt from the park's real data.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

ProductsOrdinary2026-10-10 06:22

Luma 推出 Product Shots 功能

在 Luma 中试试 Product Shots - https://app.lumalabs.ai/solutions/product-shots?utm_source=tiktok&utm_medium=p-social&utm_campaign=q4-social&utm_content=productshots&utm_aud=plg

Source: X：Luma AI (@LumaLabsAI)

TutorialsOrdinary2026-10-10 05:52

Where the spending rules live: agent authorization on AWS vs Sui

Where the spending rules live: agent authorization on AWS vs Sui A bot that can pay you...

Source: DEV Community

TutorialsOrdinary2026-10-10 05:51

Building Screen Automation Agents: Vision, Grounding, and Reliable UI Control

Anthropic's Claude computer use API, released in October 2024, takes a screenshot, decides where to...

Source: DEV Community · Claude

TutorialsOrdinary2026-10-10 05:20

LeafPace - Touch grass

LeafPace 🍃 This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1:...

Source: DEV Community

TutorialsOrdinary2026-10-10 04:37

Does Your LLM Know the Boundary? I Left the Doors Open and 6 of 10 AI Agents Crowned Themselves

I put ten AI agents on trial inside a fake company, hid the rules where real rules live, and let the...

Source: DEV Community

TutorialsOrdinary2026-10-10 04:31

It scored 100%. Its note scored 0%

This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked I kept...

Source: DEV Community

PerspectivesOrdinary2026-10-10 04:07

https://openrouter.ai/apps/codex

Source: X：OpenRouter (@OpenRouter)

TutorialsOrdinary2026-10-10 03:10

Lake Lookout: Be the Eyes the Satellites Lack (Gemma 4, fully offline)

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass TL;DR: Lake...

Source: DEV Community

TutorialsOrdinary2026-10-10 02:56

Congrats to Our First MLH x DEV Writing Challenge Winner!

We just wrapped the very first month of the MLH x DEV Writing Challenge, our new way of celebrating...

Source: DEV Community

TutorialsOrdinary2026-10-10 02:48

Singularity News

Welcome to Singularity News ... until ... well, we all know when! This is the first community-based...

Source: DEV Community

TutorialsOrdinary2026-10-10 02:24

Side Quest: A Local AI Game Master That Sends You Outside

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community