AI Intelligence Archive
浏览 AIQB 已保存的 6403 stories AI intelligenceArticles,覆盖Models、Products、Industry、Research、教程与观点方法六大分类。
Indexed articles6403
Categories6
Selected stories2
All articles
Section 30 / 161 页 · 每页 40 stories
TutorialsOrdinary
Why My LLM Feature Cost More Than It Should: Field Notes on Prompt Caching, Cache Breakpoints, and the Timestamp That Killed Every Hit
Headline: Prompt caching saves money only when the cached prefix is byte-identical across requests,...
Source: DEV Community
TutorialsOrdinary
AI Should Propose. Systems Should Verify.
AI Should Propose. Systems Should Verify. An AI agent can produce the correct action and...
Source: DEV Community
TutorialsOrdinary
Stop dragging boxes in Draw.io: Turn plain text into interactive architecture maps
Every time I need to draw an architecture diagram or document a workflow, the same thing happens: I...
Source: DEV Community
TutorialsOrdinary
Markdown Is Everywhere, and It All Started with a README
Original article: Markdown Is Everywhere, and It All Started with a README Have you noticed that...
Source: DEV Community
TutorialsOrdinary
Vibe Coding Hasn't Won. The Industry Is Misreading Its Own Data.
Originally published at zalcro.ai/guides/vibe-coding-hasnt-won The most repeated statistic in...
Source: DEV Community
TutorialsOrdinary
Structured outputs as application contracts
Your LLM Output Should Have a Contract, Not a Vibe So there I was, an AI engineer at a...
Source: DEV Community
TutorialsOrdinary
Shopping for Skills and MCP Servers (Without Getting Burned)
A year or two ago, giving an AI assistant new abilities meant waiting for the company behind it to...
Source: DEV Community
TutorialsOrdinary
I Built a 188M Mixture-of-Experts LLM From Scratch on a Free GPU
By Shivam Kumar, founder of VisionQuantech. This is the honest version — what's proven, what's...
Source: DEV Community
TutorialsOrdinary
I let my AI agents merge to production. Once.
I automated almost my entire pipeline this year, and I'd fight you to keep it that way. An agent...
Source: DEV Community
TutorialsOrdinary
Nine Bugs That Taught Me Reliability: Post-Mortem of a Zero-Cost Hybrid AI System
canonical_url: https://arielchangdev.github.io/angelina-finance-agent/ Building a hybrid local+cloud...
Source: DEV Community
TutorialsOrdinary
Building an Agentic System in .NET, Part 6: Redaction, Audit and the Safety Layer
Prompt injection is OWASP's LLM01:2025, the top vulnerability in LLM based systems, and yet most...
Source: DEV Community
TutorialsOrdinary
From Dev.to Comment to Production in 24h: Building an Inspectable Math Verification Contract in Pythos (and Fixing the Pearson Trap)
Earlier this week, I published an article here on DEV: "Why We Stopped Letting LLMs Do Raw Math:...
Source: DEV Community
TutorialsOrdinary
We turned handmade art dolls into playable 3D characters in the browser
Like Art is a marketplace for handmade art dolls - a bit under 3,000 pieces from 700+ independent...
Source: DEV Community
TutorialsOrdinary
SiliconFlow API Review 2026: Setup, Models and Real Pricing
A hands-on SiliconFlow API guide: OpenAI-compatible setup, model catalogue, rate limits and per-token prices vs DeepSeek, Together AI and DeepInfra.
Source: DEV Community · OpenAI / DeepSeek
TutorialsOrdinary
Claude Code Router v3: What Changed and How I Set It Up Now
Claude Code Router is now a desktop app and local gateway. Here's how v3.1 handles providers, model tiers, routing scripts and fallbacks for Claude Code.
Source: DEV Community · Claude
TutorialsOrdinary
Open Generative AI GitHub Repo: A Self-Hosting Teardown (2026)
Open Generative AI GitHub teardown: what the 29.7k-star repo runs locally, what needs a Muapi key, the setup commands, and the gotchas I'd check first.
Source: DEV Community
TutorialsOrdinary
Blader Humanizer in 2026: What v3.1 Changed and How I Use It
A hands-on guide to blader humanizer v3.1.0: the 26 patterns, install steps for Claude Code and Codex, voice matching, and what it still can't do for you.
Source: DEV Community · Claude
TutorialsOrdinary
Virlo in 2026: What It Is, What the API Costs, and a Python Starter
What Virlo actually is in October 2026, how its pay-as-you-go API is priced, why Orbit and Comet are deprecated, and a working Python script to start with.
Source: DEV Community
TutorialsOrdinary
Free LLM API Tiers in October 2026: What's Left and How I Chain Them
A practical October 2026 guide to every free LLM API worth using: real rate limits, the catches nobody mentions, and a Python fallback chain that survives 429s.
Source: DEV Community
TutorialsOrdinary
Claude Code in VS Code: The Official Extension, Set Up Properly
Claude Code in VS Code has an official Anthropic extension now. Install, permission modes, checkpoints, CLI vs panel, and the settings I'd change on day one.
Source: DEV Community · Claude
TutorialsOrdinary
Can Claude Generate Images? What Actually Works in 2026
Can Claude generate images? Not natively. Here is what it can output instead (SVG, HTML, Pillow code) and how to wire Claude Code to a real image model.
Source: DEV Community · Claude
TutorialsOrdinary
How Chatbots Remember: Short Term, Long Term and Everything in Between
Product teams are adding memory to AI assistants to improve continuity and personalization. Memory is...
Source: DEV Community
TutorialsOrdinary
Beyond Kafka and Redis, Part 2: An AI Chat Backend on NATS 2.15
In part 1 I walked through the NATS building blocks one at a time: subjects, request-reply, JetStream...
Source: DEV Community
TutorialsOrdinary
Your API's Newest Users Are Agents: Designing for Non-Human Clients
Introduction Your API's newest users are agents. They don't read docs, they don't browse...
Source: DEV Community
TutorialsOrdinary
Taming the Exchange API: Handling -4509 Errors and the F-065 Retry Mechanism in Quant Systems
Taming the Exchange API: Handling -4509 Errors and the F-065 Retry Mechanism in Quant...
Source: DEV Community
TutorialsOrdinary
Cut LLM Document-Extraction Cost by 85% Without Losing Accuracy
Most production LLM extraction pipelines route every field through a frontier model, every time. It...
Source: DEV Community
TutorialsOrdinary
Where Claude Code puts your MCP server's instructions: in a user turn, not the system prompt, cut at 2,048 characters
20 of 20 claude -p runs on Claude Code 2.1.285 opened our stdio MCP server with server/discover, a...
Source: DEV Community · Claude
TutorialsOrdinary
Ventana seca: finding the dry hour to get outside in Panama's rainy season, with Gemma on my laptop
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
Source: DEV Community
TutorialsOrdinary
People Won't Go Outside so I made this
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
Source: DEV Community
TutorialsOrdinary
The $250 Agent Challenge: Build Something Real With Docker Cloud Sandboxes
What would you build if someone handed you $250 of cloud compute for AI agents? That's not a...
Source: DEV Community
TutorialsOrdinary
Your AI Agent Has a Context Budget: Treat It Like a CPU Budget
The 3 AM page Picture this. You get paged at 3 AM for a production outage. A teammate...
Source: DEV Community
TutorialsOrdinary
Claude Code vs Codex CLI vs Cursor: An Honest Field Guide for Working Developers
Claude Code vs Codex CLI vs Cursor: An Honest Field Guide for Working Developers I use all...
Source: DEV Community · Claude / Cursor
TutorialsOrdinary
Practical Patterns for AI Agent Governance in Production
When an AI agent starts calling real systems – deploy pipelines, billing, CRM, data workflows –...
Source: DEV Community
TutorialsOrdinary
Self-Hosting an AI Assistant on CasaOS: A Step-by-Step OpenMuse Install Guide (Pitfalls Included)
How to deploy OpenMuse — a self-hosted AI chat assistant that can also manage your CasaOS server —...
Source: DEV Community
TutorialsOrdinary
Changing what my phone agent was shown beat changing the model
This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked On 18...
Source: DEV Community
TutorialsOrdinary
Bug Dex - Gotta Find Em All!
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
Source: DEV Community
TutorialsOrdinary
Code review is your last line of defense against agent pull requests
Agent-authored PRs went from under 1% to 27.6% of GitHub pull requests in fourteen months. Acceptance rates look fine; the failures land in places review was never built to check. Here is what to gate on.
Source: DEV Community
TutorialsOrdinary
Federated Threat Intelligence: Sharing IOCs Without Sharing Content
The fundamental problem in threat intelligence is latency. Organization A detects a novel prompt...
Source: DEV Community
TutorialsOrdinary
The Flattery Tax: I pressure-tested 29 LLMs with confident wrong users — the frontier held, the small ones folded
This is a submission for the Kaggle Benchmarking Challenge What I Benchmarked The...
Source: DEV Community
ModelsOrdinary
Ben Affleck 谈写 Python 与理解 CNN
how do you like them convolutions
Source: X:Thomas Wolf(Hugging Face 联创/CSO) (@Thom_Wolf) · Hugging Face