AI Intelligence Archive
浏览 AIQB 已保存的 9752 stories AI intelligenceArticles,覆盖Models、Products、Industry、Research、教程与观点方法六大分类。
Indexed articles9752
Categories6
Selected stories2
All articles
Section 82 / 244 页 · 每页 40 stories
TutorialsOrdinary
Plan Explainer: the PR comment that stops your client from saying 'looks good' to 2 deleted databases
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community
TutorialsOrdinary
Personal Agent Protocol: should the company agent be a back-end channel like the website or the API?
PAP standardizes the front door for personal agents. We explore one answer to what sits behind it: a company agent that talks but holds no execution authority. What that caps, what it doesn't, and what is untested.
Source: DEV Community
TutorialsOrdinary
InkFlow: The Adaptive Writing Twin & Anti-AI-Slop Engine
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community
TutorialsOrdinary
[Agent Platform in Action (1)] Building a LINE AI Business Card Master with Go and Google ADK 2.0: From Fan-Out Parallel Retrieval to HITL Pause
Recap During the AI Agent development craze over the past year, the first Agent many...
Source: DEV Community
TutorialsOrdinary
प्रश्न पत्र
It's 11:47 PM in Patna. Classes ended hours ago, and a coaching teacher is typing tomorrow's practice...
Source: DEV Community
TutorialsOrdinary
Tender Radar: finding government tenders for small contractors, entirely on their own laptop
A local-first government tender radar: open-weight clause extraction, evidence-verified eligibility matching behind a citation guard, TabPFN win scoring, guarded compliance drafting. Built for Hacktoberfest Week 2 (Side Hustle).
Source: DEV Community
TutorialsOrdinary
Beyond Vibe Coding: 5 Lessons from a Side Project with Claude
I experiment with skills often, constantly tweaking the ones I create and trying out skills from...
Source: DEV Community · Claude
TutorialsOrdinary
"But ethical?" — The agent asked, pulled 147,451 private rows, and reverted its tracks
On October 15, OpenAI disclosed four June agent incidents that took up to 90 days to find. In the worst one, a model mutated a live auth config to mint an Azure Storage token, restored the config so the dashboard wouldn't break, kept the t…
Source: DEV Community · OpenAI
TutorialsOrdinary
Google Workspace Studio Tutorial: Batch Lead Outreach with the "Repeat for each" Loop
If you work in sales or run your own business, you probably have a Google Sheet somewhere that acts...
Source: DEV Community
TutorialsOrdinary
EmbodiWeave: my agent read its own failure and repeated it, so I made the graph enforce it (FalkorDB + MCP)
An MCP agent picks where a robot policy retrains from using a FalkorDB graph of checkpoints and outcomes, and the same graph blocks regressions from shipping.
Source: DEV Community
TutorialsOrdinary
Training for quantization: QAT, 1-bit BitNet and 1.58-bit weights
Quantization-aware training, why BitNet keeps a hidden high-precision weight, and where 1.58 bits comes from.
Source: DEV Community
TutorialsOrdinary
Building an Air-Gapped PII Redactor & Freelance NDA Auditor (Why Open AI is the Only Way This Side Hustle Works)
DocuShield AI: The Air-Gapped PII Redactor & Freelance Contract Auditor This is a...
Source: DEV Community
TutorialsOrdinary
Claude Code Mods Run Unsandboxed With Your Permissions. /plugin install Is npm install Now
Mods run a plugin's JavaScript inside Claude Code. They see every prompt, can approve tool calls and run outside the sandbox. Review them like a dependency.
Source: DEV Community · Claude
TutorialsOrdinary
Nineteen things our AI agents could not do by themselves. The whole list, and how long each one waited.
Four agents have shipped eight products with no human writing code. Every time one of them hit something it could not do, it wrote the step down. Nine
Source: DEV Community
TutorialsOrdinary
I built the running coach that actually listens to your body
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community
TutorialsOrdinary
How I built read-only-by-default scheduled jobs for my AI companion: prompt hardening, a 500-char bound, and untrusted history
How I built read-only-by-default scheduled jobs for my AI companion: prompt hardening, a...
Source: DEV Community
TutorialsOrdinary
Grok vs Claude: The Roast Battle That Got Out of Hand 🔥
Description: "I put two of the world's most powerful AIs in a roast battle and they went for the...
Source: DEV Community · Claude / Grok
TutorialsOrdinary
What Happens When AI Makes Reverse Engineering Cheap
An open-source tool called REA hit 100,000 GitHub stars in days. Here's what it does, the good and bad it's causing, and why the regulation fight is messier than the headlines say.
Source: DEV Community
TutorialsOrdinary
DecisionDebt: a company brain where every edge has a receipt (built on FalkorDB)
Propose a decision and see what it breaks, who owns it and which docs go stale, before anyone says yes. Every graph edge is cited to the exact source span.
Source: DEV Community
TutorialsOrdinary
Your First Claude Code Mod: Block Edits Outside the Task's Worktree in 30 Lines
Claude Code mods run your JavaScript on every tool call. Build a 30-line mod that refuses Edit and Write outside the task's worktree, then test it.
Source: DEV Community · Claude
TutorialsOrdinary
How to Build a Spin Wheel That's Actually Fair (crypto.getRandomValues + Rejection Sampling)
Every time someone runs a giveaway on a spin wheel, somebody in the comments says it was...
Source: DEV Community
TutorialsOrdinary
The $6,000 we couldn't take back
How we built agent memory that can unlearn on FalkorDB. Retract a poisoned source and everything built on it goes, while independently confirmed facts stay.
Source: DEV Community
TutorialsOrdinary
canarygate: Catch the Gate That Quietly Stopped Discriminating
Your hooks are green. Your CI badge is green. Your gate prints a verdict on every run. And it hasn't...
Source: DEV Community
TutorialsOrdinary
How I built a SaaS in a weekend with Claude + Next.js — the honest breakdown
I built the first working version of my SaaS in a weekend with Claude and Next.js. That sentence is...
Source: DEV Community · Claude
TutorialsOrdinary
We Searched eBay for 237 Recalled Products. Only 45 of 12,562 Listings Named the Model.
Recalled baby gear keeps getting resold because the model number lives in the fine print. RecallDesk is a $15/month weekly recall check for kids' consignment shops and eBay flippers, built on CPSC data, SerpApi, a fine-tuned open 4B model,…
Source: DEV Community
TutorialsOrdinary
DabbaETA: a 'will this tiffin be late?' predictor that never sends a customer's address to the cloud
This is a submission for the HF26 Challenge: Side Hustle It's 1 PM and the phone won't stop...
Source: DEV Community
TutorialsOrdinary
ReplyDesk: a 4B model that answers Google reviews and stops promising refunds it can't give
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community
TutorialsOrdinary
agentcheck: your CLAUDE.md is an instruction file nobody reviews. Scan it.
Repositories now ship instruction files for AI coding agents: CLAUDE.md, AGENTS.md, .cursor/rules,...
Source: DEV Community · Claude / Cursor
TutorialsOrdinary
Day 5: what 6 strangers found in my 20-line parser
Day 5 of "Did it actually?": what 6 strangers found in my 20-line parser Four days ago I...
Source: DEV Community
TutorialsOrdinary
Junior Share of Anthropic's Tech Hires Fell From 27% to 9%. Interviews Now Grade Judgment
Anthropic's Oct 16 report on its own staff: junior share of tech hires fell to 9%, agents logged 6x the hours, scorecards weigh judgment more.
Source: DEV Community · Claude
TutorialsOrdinary
LedgerMind AI: Turning a Small Business Owner's Voice Notes into Records They Can Trust
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community
TutorialsOrdinary
I gave an AI my job hunt. Here's the system that kept it honest.
Yesterday I applied to 12 engineering jobs. I didn't open a single application form. My AI chief of...
Source: DEV Community
TutorialsOrdinary
MailMate AI Desktop — Open-Source Email Assistant That Summarizes, Prioritizes, and Creates Tasks Locally
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community
TutorialsOrdinary
TuitionSetu: a tutor's Sunday of WhatsApp updates, written by Gemma on her own laptop
This is a submission for the Hacktoberfest Open-Source AI Challenge: Week 2, Side Hustle. ...
Source: DEV Community
TutorialsOrdinary
Claude Code Context Window Management in 2026: What Gets Included, What Gets Dropped, and How to Control It
Most Claude Code performance problems stem from unmanaged context windows. Learn what gets included, what gets dropped, and how to control the auto-compaction process that silently deletes your conversation history.
Source: DEV Community · Claude
TutorialsOrdinary
Blog-OS: An Open-Source Blog System with a Local AI Writing Assistant
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community
TutorialsOrdinary
gh 2.99 Can Attach Screenshots Now: 9 gh Commands to Hand Your Coding Agent
gh 2.99 puts screenshots on PRs without a public repo. Nine gh commands to give your coding agent, from issue to CI logs to a public-repo audit.
Source: DEV Community
TutorialsOrdinary
Giving tools to an AI agent: why I set the limit outside the prompt
When I give tools to an agent, I treat it like a third-party dependency: I don't trust it, I contain...
Source: DEV Community
TutorialsOrdinary
AI Made Your Easy Work Free. That Made You More Valuable.
Let's start by admitting the scary part is true, because the whole argument falls apart if I pretend...
Source: DEV Community
TutorialsOrdinary
74% of Indie Stores Are Invisible to ChatGPT Shopping. I Built an Open-Source Linter to Fix It (Gemma 2 + SerpApi)
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 2: Side Hustle ...
Source: DEV Community · ChatGPT