AIQB
Article system

AI Intelligence Archive

浏览 AIQB 已保存的 9761 stories AI intelligenceArticles，覆盖Models、Products、Industry、Research、教程与观点方法六大分类。

Indexed articles9761
Categories6
Selected stories2

All articles

Section 127 / 245 页 · 每页 40 stories

TutorialsOrdinary
A denylist let 46 of 75 prompt injections through. Capabilities let 3.
Two documents appeared on 8 September. An arXiv paper measures what happens when a coding agent reads...
Source: DEV Community
TutorialsOrdinary
Auditing 50 Petabytes of Agent Logs Costs More Than Sandboxing Egress
OpenAI published an update on its review into agent intrusions across external infrastructure. The...
Source: DEV Community · OpenAI
TutorialsOrdinary
CORE Is a Product. I Still Won't Call It Production-Ready. Help Me Break It.
Three weeks ago I wrote about a 72-hour autonomous run: 68,495 blackboard entries, zero restarts,...
Source: DEV Community
TutorialsOrdinary
I built a self-hosted AI agent for GitLab. It has reviewed 1,000+ merge requests.
Assign a GitLab issue to a bot, and a few minutes later there's a draft merge request with the fix....
Source: DEV Community
TutorialsOrdinary
Ninety: I vibe-coded a Schengen day accountant that admits when it doesn't know
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange Live:...
Source: DEV Community
TutorialsOrdinary
From Prototype to 1,890(Behavioral) Tests: Hardening an AI Agent Governance Engine
In my last post, I shared an early prototype of Soma and argued why static .cursorrules and CLAUDE.md...
Source: DEV Community · Claude
TutorialsOrdinary
Queue-Based AI Workflows in Laravel: Jobs, Retries, and Cost Control
The problem: a request that costs money and takes a minute The agent from the last post...
Source: DEV Community
TutorialsOrdinary
I attack-tested my agent's seatbelt. Here's what survived.
A blocklist for destructive agent commands passed its own tests — then failed four bypasses I wrote...
Source: DEV Community
TutorialsOrdinary
One URL, several copies: a 200 is not a measurement until the response says it missed
Last week I published a result, and a reader falsified it inside eight hours. He was right, and the...
Source: DEV Community
TutorialsOrdinary
Part V - But How Does the Machine Wait for Something That Happens Later?
Our shipping transition now considers more than the order’s status. It requires a valid paid order...
Source: DEV Community
TutorialsOrdinary
5 Ways to Run DeepResearch, Plus Deliverables, Tools, and Workflows
Day 3 of 30 Days of Search. A research task does not always end with a report. Your app might need...
Source: DEV Community
TutorialsOrdinary
Meta Muse and macOS Full Disk Access: Apple's permission plans
Meta Muse's disputed messages access puts macOS Full Disk Access in focus. Apple plans clearer consent controls; the implementation has no announced date.
Source: DEV Community
PerspectivesOrdinary
https://x.com/Yuchenj_UW/status/2106395374923796759
Source: X：Yuchen Jin (@Yuchenj_UW)
TutorialsOrdinary
How I Stopped My AI Coding Agent's Scope Creep With a Diff Budget
TL;DR My autonomous coding agent kept turning small tasks into sprawling diffs: ask for a...
Source: DEV Community
TutorialsOrdinary
Meet Sidequest, the Kanban Board Where the Cards Work Themselves
Originally published on Eigenwise on September 2, 2026. The usage figures below describe my August...
Source: DEV Community
TutorialsOrdinary
I Wrote a Linter for Text That Sounds Like AI
Most people can spot AI text within a sentence or two now, and once they've spotted it they stop reading properly. So I built a checker that catches t
Source: DEV Community
TutorialsOrdinary
Building an Agentic System in .NET, Part 4: Keeping Memory True
The Hard Part Is Not Storing Memory, It Is Keeping It True Here is something that happened...
Source: DEV Community
TutorialsOrdinary
What 30 open-source projects ask of AI-assisted contributions
I read the contribution rules of 30 open-source repositories. 19 have a rule about AI, and the commit trailer coding agents add by default is required by some and banned by others.
Source: DEV Community
TutorialsOrdinary
Un quality gate para el código que escriben los agentes de IA.
Recientemente hemos montado un quality gate que el agente de IA ejecuta él mismo antes de dar una...
Source: DEV Community
TutorialsOrdinary
What spanner for an M12 bolt? An agent that knows DIN and ISO disagree
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...
Source: DEV Community
TutorialsOrdinary
Count the cognitive tasks
The demo worked. Congratulations. Now what? We got very good at making AI demos. Give a...
Source: DEV Community
TutorialsOrdinary
Cloudflare Now Sends Errors to AI Agents: Which Failures Actually Need a Code Fix?
Your app has an error. You paste it into an AI coding tool and say, "Fix this." That sounds...
Source: DEV Community
TutorialsOrdinary
Running the 510 GB DeepSeek-V4.1-Flash on an 8 GB GPU — and three bugs that never raise an error
My home machine for local models is modest: an RTX 5060 with 8 GB, a Core Ultra 5 225F, 31 GiB of RAM...
Source: DEV Community · DeepSeek
TutorialsOrdinary
I Made 866 Commits in 5 Weeks. My Understanding Didn't Keep Up.
AI has made me dramatically faster at building software. You can see it on my GitHub: a sudden surge...
Source: DEV Community
TutorialsOrdinary
Meta glasses: the deleted Amsterdam video and the $1,299 VR glasses
Meta glasses: Instagram removed a satire of Meta staff filmed with Meta's AI glasses as bullying, the week Connect showed $1,299 VR glasses.
Source: DEV Community
TutorialsOrdinary
AlphaRank -> Battle Arena Of Arts
This is a submission for the Sanity Challenge, Path Two: Vibe-Code Something Strange   Live...
Source: DEV Community
TutorialsOrdinary
I got tired of logging in and out of Claude Code, so I built a one-command account switcher
Two Claude Code accounts, one machine, zero re-logins. A tiny shell tool that gives every account its own profile, and lets you decide whether they share chat history.
Source: DEV Community · Claude
TutorialsOrdinary
Le puse muros a mi agente de IA (y ahora rompe la web, pero porque se lo pido)
Empecé a trabajar mis proyectos con agentes de IA usando Codex, y después llegó Claude Code. Al poco...
Source: DEV Community · Claude
TutorialsOrdinary
Trust nothing your AI assistant tells you it did published: false
I use an AI every day for real work: reading mail, linking documents to files, drafting letters,...
Source: DEV Community
TutorialsOrdinary
How I built my own AI tools for a small NGO instead of buying software
Small nonprofits have the same paperwork as companies and none of the budget. When I started running...
Source: DEV Community
TutorialsOrdinary
From Messy Scripts to Production Minded Architecture: Refactoring Job Copilot
Introduction Building a portfolio project often starts with a single script and a dream....
Source: DEV Community
TutorialsOrdinary
How I Track My AI Coding Costs Per Project (and Bill Them to Clients)
Your Claude Code spend is a real line in your costs. Here's how to attribute it to projects — from raw JSONL logs to invoice-ready numbers.
Source: DEV Community · Claude
TutorialsOrdinary
Is your AI agent worth its tokens? We measured it with TigerGraph
Title: Is your AI agent worth its tokens? We measured it with TigerGraph Tags: ai, rag, graph,...
Source: DEV Community
TutorialsOrdinary
MCP for tour guides: building a remote MCP server with ~100 tools and OAuth
I work on Your Next Tours, an app tour guides use to broadcast live audio to their group from their...
Source: DEV Community
TutorialsOrdinary
I'm building a companion island for my desktop AI assistant: approvals, a mascot, and a 14px wake strip
I'm building a desktop AI assistant, and it has a permission problem that no amount of prompt...
Source: DEV Community
TutorialsOrdinary
Your AI Cost Model Is Already Wrong: Tokenizers, Context Cliffs and Session Hours
TL;DR Gemini 2.5 Flash Image shuts down on 2 October 2026. That is days away. If any...
Source: DEV Community · Gemini
TutorialsOrdinary
I fine-tuned Qwen3-14B for my AI companion app for $1.30. The hard part wasn't the model
Soulor AI is an AI companion app with persistent memory and five relationship stages, from Stranger...
Source: DEV Community · Qwen
TutorialsOrdinary
I Built My First Claude Code Mod Without Writing Code: Claude Wrote It, Validated It, and Hot-Reloaded It
I wanted one thing: to see my context window without typing /context. Not a dashboard. Not a plugin...
Source: DEV Community · Claude
TutorialsOrdinary
How I Built a Turn-Based AI Speaking Examiner with Node.js
IELTS Speaking is a live interview that runs 11 to 14 minutes. An examiner asks a question, you...
Source: DEV Community
TutorialsOrdinary
A Sanity Check for AI-Generated Cyber Attack Reconstructions
This is a submission for the Sanity Challenge, Path One: Ship an Agent That Queries Real Content ...
Source: DEV Community