Article system

AI Intelligence Archive

浏览 AIQB 已保存的 6464 stories AI intelligenceArticles，覆盖Models、Products、Industry、Research、教程与观点方法六大分类。

Indexed articles6464

Categories6

Selected stories2

All articles

Section 85 / 162 页 · 每页 40 stories

ResearchOrdinary2026-09-22 20:44

Disaggregated Quantization: Specializing LLM Prefill and Decode

Prefill and decode reward different approaches to quantization: low-precision arithmetic accelerates prompt processing, while compact weights reduce memory traffic during generation. We propose "disaggregated quantization" (DQ), which spec…

Source: arXiv · Qwen / Llama

ResearchOrdinary2026-09-22 20:36

Error Bounds for Statistical Estimators in BTL Model with Parametric Multivariate Utility Functions

We study preference elicitation under the Bradley-Terry-Luce (BTL) model where the true partworth vector is unknown and has to be estimated as a parameter with elicited preference information. The set of selected pairwise queries is non-un…

Source: arXiv

TutorialsOrdinary2026-09-22 20:25

TypeSafe’s JEV Model: Is It Really 193x Faster and 444x Cheaper?

TypeSafe launched Jev on September 15 and it reached OpenRouter three days later. Since then nearly...

Source: DEV Community

ResearchOrdinary2026-09-22 20:23

TriWorldBench: A Tri-View Consistency Perspective on Embodied World Models

Embodied world models predict the outcomes of robot actions to support learning and planning. For robots equipped with head and wrist cameras, this requires complementary views: the head view captures the overall task, while wrist views re…

Source: arXiv

TutorialsOrdinary2026-09-22 20:20

I Built an AI Agent That Does X — Here's What Actually Broke

Most posts about AI agents show you the demo. The demo always works. Nobody writes about the part...

Source: DEV Community

TutorialsOrdinary2026-09-22 20:19

I Cut 2,490 Agent Test Runs to 206 and Kept the Same Coverage

The full matrix was 83 agents × 30 scenarios = 2,490 runs. Each one a real LLM call, 30–80 seconds....

Source: DEV Community

TutorialsOrdinary2026-09-22 20:12

Memory, not speed, is the hard part of running an LLM on a phone

I ship an Android app (Onira) that generates a personalized hypnosis/relaxation script on-device with...

Source: DEV Community

TutorialsOrdinary2026-09-22 20:01

SIMURG: A Guard That Catches LLM Hallucinations Mid-Stream and Heals Them

Your LLM looks fine in the demo. Then it ships. Somewhere between "it works on my machine" and "a...

Source: DEV Community

TutorialsOrdinary2026-09-22 20:00

How do you stop an LLM from leaking API keys in the code it writes? Default to secret

On July 22 I typed a one-line prompt on a test app: a widget built on a well-known REST API, the kind...

Source: DEV Community

TutorialsOrdinary2026-09-22 20:00

One Month In: The Number That Finally Moved Wasn't the One I Expected

This blog turned one month old this week. I'd built a habit of checking four dashboards every few...

Source: DEV Community

TutorialsOrdinary2026-09-22 19:51

I Told a PR Nothing Would Break. Qodo Checked.

Every PR description is a claim. "No consumers of this API were changed." "Safe to merge." Most...

Source: DEV Community

TutorialsOrdinary2026-09-22 19:46

Think smaller: why specialist SLMs beat frontier models in production

Most agent tasks do not need a frontier model. The subtasks inside a production agent are largely...

Source: DEV Community

TutorialsOrdinary2026-09-22 19:15

A decorrelated bot that loses money is just a diversified way to lose money

probe

Source: DEV Community

TutorialsOrdinary2026-09-22 19:00

I built a self-hostable AI data analyst — 4 agents, sandboxed code execution, your choice of LLM

Every time I needed to explore a dataset quickly, the same wall appeared: spin up a notebook, deal...

Source: DEV Community

TutorialsOrdinary2026-09-22 19:00

AI Coding Tip 037 - Stop Patching Blind

Old code, new AI, same unwritten test suite. TL;DR: Patch code that never had a test written for...

Source: DEV Community

TutorialsOrdinary2026-09-22 18:40

Build a Multi-Agent RAG Legal Assistant with LangGraph, FastAPI, and Streamlit (Beginner Guide)

Retrieval-Augmented Generation (RAG) sounds complex, but the core concept is straightforward: instead...

Source: DEV Community

TutorialsOrdinary2026-09-22 18:33

Keeping credentials out of your coding agent’s model context

I always had a slightly bad feeling about the credentials my coding agent could access. Did I secure...

Source: DEV Community

TutorialsOrdinary2026-09-22 18:30

A Transaction Hash Is Not an Audit Trail for Onchain Automation

A transaction hash tells us that something happened onchain. It does not tell us which information...

Source: DEV Community

TutorialsOrdinary2026-09-22 18:21

I built ChibiRigKit: turning a single character image into an animated 2D rig

I built ChibiRigKit, an open-source tool that turns a single character illustration into an animated...

Source: DEV Community

TutorialsOrdinary2026-09-22 18:15

EU Child Safety Panel Report Signals Stricter Rules and Age Verification Direction

The European Commission has received the final report from its Special Panel on Child Safety Online,...

Source: DEV Community

TutorialsOrdinary2026-09-22 17:48

Did canceling the agent stop the GPU job?

The agent stopped the training run. The GPU cluster did not. Agent Evaluation Case #003 ...

Source: DEV Community

TutorialsOrdinary2026-09-22 17:46

How to Build a Fast Decision Layer for AI Agents with TypeSafe Jev

Most AI agent architectures use the same large language model for every task: planning, writing, tool...

Source: DEV Community

TutorialsOrdinary2026-09-22 17:40

Keyword Research with AI Agents and Google Search Console

Keyword Research with AI Agents and Google Search Console Manual keyword research is slow...

Source: DEV Community

TutorialsOrdinary2026-09-22 17:38

8 of my AI agent's 30 test calls failed. Every one was my fault.

The record said there was a gas leak. It did not say where. { "urgency": "emergency", ...

Source: DEV Community

TutorialsOrdinary2026-09-22 17:21

What Did You Deliberately Leave Out of Your MVP?

What Did You Deliberately Leave Out of Your MVP? Most MVP posts show what made it into...

Source: DEV Community

TutorialsOrdinary2026-09-22 17:18

From Quantity to Quality: A Risk-Based Approach to AI-Assisted QA at Scale

We write more tests than ever, yet bugs still reach production. This post introduces a risk-based...

Source: DEV Community

TutorialsOrdinary2026-09-22 17:01

Jev is now open to everyone: what a "System One" model costs, and how to start with $5 in free credit

Intro: Jev launched Sep 15 and drew a 140k waitlist in days. On Sep 20 TypeSafe removed the waitlist...

Source: DEV Community

TutorialsOrdinary2026-09-22 16:40

I built a community tool because my browser bookmarks went to die. Now, I need your help to scale it.

Let’s be honest: we all have a graveyard of bookmarks. Every time I see a cool open-source CLI tool...

Source: DEV Community

TutorialsOrdinary2026-09-22 16:31

3 Developer Archetypes That Can Break a Team

There are developers who make a team faster. There are developers who make a team better. And there...

Source: DEV Community

TutorialsOrdinary2026-09-22 16:26

The Curiosity Gap: Why We've Stopped Asking Questions

In a comment some weeks ago (link) i wrote about how it doesn't matter if you are using AI or not, or...

Source: DEV Community

TutorialsOrdinary2026-09-22 16:20

BMAD Ate My Month: When Spec-Driven Development Is Too Much

On September 5 I deleted 1,782 files from my autopilot's repository in one commit. Agents, templates,...

Source: DEV Community

TutorialsOrdinary2026-09-22 16:10

Fine-Tune, Deploy and Use LLM As AI Agent

In this video I continue the fine-tuning series on my channel. This time I go through the whole...

Source: DEV Community

TutorialsOrdinary2026-09-22 16:05

TrustNotch: tamper-evident audit logs for AI agents (that your agent can sign up for by itself)

The first time an agent I built did something I could not explain, I went to check what it had...

Source: DEV Community

TutorialsOrdinary2026-09-22 16:05

Your MCP Tool Just Returned a Secret. Did It Need To?

“Done. Here's the download link.” A perfectly ordinary answer from an AI agent. Also the moment a...

Source: DEV Community

TutorialsOrdinary2026-09-22 16:04

Claude Code Hooks – Safety Through Invariants

Info: This is a later upload of an introductory post I made a few months ago. 1...

Source: DEV Community · Claude

TutorialsOrdinary2026-09-22 15:58

Deploying Snowflake Cortex Agent and Knowledge Graph with ServiceNow MCP Server

Introduction ServiceNow provides a feature called MCP Server. It allows various...

Source: DEV Community

TutorialsOrdinary2026-09-22 15:29

Treat streamed LLM output as an uncommitted draft

I'm a developer working on Paramour.chat, an LLM roleplay app where, of course, exchanges need...

Source: DEV Community

TutorialsOrdinary2026-09-22 15:22

Two Weeks In: A 15-Year QA Veteran, Back to Being the New Guy

I started last Monday. Today it's been exactly two weeks. Here's the funny part. I've spent 15...

Source: DEV Community

TutorialsOrdinary2026-09-22 15:12

Cheap RAG in Go with Gemini File Search: no vector DB, two calls, one hosted store

Hello, I'm Maneshwar, and I'm building LiveReview — a blast-radius aware AI code review built for...

Source: DEV Community · Gemini

TutorialsOrdinary2026-09-22 14:57

Your AI eval is green because it never called the model

We run an eval suite on every PR. Seven fixtures, four metrics, deterministic, no API key, no...

Source: DEV Community