Article system

AI Intelligence Archive

浏览 AIQB 已保存的 9740 stories AI intelligenceArticles，覆盖Models、Products、Industry、Research、教程与观点方法六大分类。

Indexed articles9740

Categories6

Selected stories2

All articles

Section 38 / 244 页 · 每页 40 stories

TutorialsOrdinary2026-10-31 19:15

Shopify’s AI Governance Shift Shows How Adoption Can Become Cultural

Shopify’s approach to AI adoption was designed to make the technology a normal part of work, rather...

Source: DEV Community

TutorialsOrdinary2026-10-31 18:47

We took over ChatGPT accounts: the MathLive postMessage chain, and the 20-line audit for your own listeners

A shared ChatGPT link, a math keyboard library listening to any sender, an iframe that inherits chatgpt.com, a CSP bypass through YouTube's oembed, and the session token: full account takeover, fixed Oct 26, $5k bounty. The attack chain st…

Source: DEV Community · ChatGPT

TutorialsOrdinary2026-10-31 18:30

Big Travel Brands Lead AI Search, but Inspiration Queries Leave Room for Smaller Sites

Major travel brands account for a substantial share of visibility in Google AI Overviews and ChatGPT...

Source: DEV Community · ChatGPT

TutorialsOrdinary2026-10-31 18:23

Architecting Stateful AI Agents in Laravel: Bridging n8n, MCP, and RAG for Production Workflows

The demo works flawlessly. You ask the AI agent to analyze a customer's billing history, query the...

Source: DEV Community

TutorialsOrdinary2026-10-31 18:06

Butu 🧸: a friendly browser companion that gets lonely when you leave your work

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine. ...

Source: DEV Community

TutorialsOrdinary2026-10-31 18:05

ELEGY - a séance for abandoned repositories

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

Source: DEV Community

TutorialsOrdinary2026-10-31 18:05

GitGhost: The Haunted Code Archaeologist & Legacy Tech-Debt Exorcist

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the...

Source: DEV Community

TutorialsOrdinary2026-10-31 18:00

Debugging in the Agentic Era

Coding agents write frontend code fast, but they can't see it run. This is the flow I use to fix...

Source: DEV Community

TutorialsOrdinary2026-10-31 17:15

Google Opens Connected Apps Platform for AI Mode and Gemini

Google has launched a Connected Apps Platform that enables third-party applications to run within AI...

Source: DEV Community · Gemini

TutorialsOrdinary2026-10-31 17:10

ghost.py: My Terminal Is Haunted (and It Remembers Me)

What I Built ghost.py possesses your shell. You run commands through it as usual, and...

Source: DEV Community

TutorialsOrdinary2026-10-31 17:03

Aoandon: Hearn's ghost stories in Japanese, retold at five JLPT levels

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine In...

Source: DEV Community

TutorialsOrdinary2026-10-31 16:58

Every repository is haunted

git, a 3.3 GB model that never leaves the laptop, and 69 references to files that no longer exist.

Source: DEV Community

TutorialsOrdinary2026-10-31 16:56

Architecting a Human-in-the-Loop AI Support Agent with n8n and Laravel

Deploying fully autonomous AI agents in customer-facing environments is a massive operational risk....

Source: DEV Community

TutorialsOrdinary2026-10-31 16:13

I made $0 from my side project for 8 months. Then one furious email at 2am changed everything.

For eight months, the most-visited tab in my browser was a Stripe dashboard that said $0.00. I'd...

Source: DEV Community

TutorialsOrdinary2026-10-31 16:13

Kavach, final round: a fraud investigator that shows its work, on TigerGraph

TigerGraph x Hacker House Goa 2026, final round. Team PixelPaws: Subhojyoti Maity and Arni...

Source: DEV Community

TutorialsOrdinary2026-10-31 15:36

What Broke After I Moved My Agent's Rules into a CLI (And How Synthetic Scars Reshaped ag_ops v2.1)

How four embarrassing bugs in v1, two sharp comment threads, and Randal L. Schwartz's Synthetic Scars...

Source: DEV Community

TutorialsOrdinary2026-10-31 15:31

Haunted Terminal: a local spirit that can change your prompt, but not your shell

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine ...

Source: DEV Community

TutorialsOrdinary2026-10-31 14:56

Ofrenda: a keeper for stories that runs entirely on your laptop

This is my submission for the Hacktoberfest Open-Source AI Challenge, Week 4. The theme was Ghost in...

Source: DEV Community

TutorialsOrdinary2026-10-31 14:42

Ghost in the Machine: Possessed Terminal & Día de los Muertos Living Ofrenda with Open-Source AI

👻 What I Built Between October 31 (Halloween) and November 1–2 (Día de los Muertos), the...

Source: DEV Community

TutorialsOrdinary2026-10-31 14:35

I built a self-hosted AI list that checks itself weekly

Self-hosted AI moves fast. A list that was right in March has dead links by June, and nobody notices...

Source: DEV Community

TutorialsOrdinary2026-10-31 13:44

I Built RepoGeist: An Open-Source AI That Uncovers the Ghosts in Your Git History

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the...

Source: DEV Community

TutorialsOrdinary2026-10-31 13:06

I can't ask my old team lead why anymore, so I built a séance

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 4: Ghost in the Machine. A...

Source: DEV Community

ResearchOrdinary2026-10-31 12:57

Evidence-grounded large language models guide perovskite solar cell design and optimization

Using large language models to interpret experimental evidence, design discriminating experiments and formulate well-supported mechanistic explanations remains a central challenge in materials research. Here we establish PSM-Bench, an 800-…

Source: arXiv

ResearchOrdinary2026-10-31 12:55

TopoQuant: Topological Framework to Characterize Behavioral Shifts in Quantized Large Language Models

Post-training quantization (PTQ) reduces the com putational cost of large language models (LLMs), but it can introduce internal structural and behavioral changes that are not captured by traditional metrics such as accuracy and per plexity…

Source: arXiv

ResearchOrdinary2026-10-31 12:51

Autonomous Analysis of Thermoelectric Materials Big Data by Multi-Agentic AI and Construction of a Knowledge Base and Specialized AI

Extracting knowledge from large databases of experimental materials data requires repeated analyses and reusable records of their choices and results. We developed Multi-Agentic AI (MAA), a multi-agent system in which AI agents with distin…

Source: arXiv

ResearchOrdinary2026-10-31 12:48

XLA from the Trenches: Correctness on TPU Workloads at Scale

Accelerating modern foundational models has pushed domain-specific compilers toward increasingly complex, multi-tiered optimization pipelines. However, this heavy optimization focus introduces delicate tradeoffs between peak execution perf…

Source: arXiv

ResearchOrdinary2026-10-31 12:43

Log-Driven Semantic Tuning for Mixed Integer Programming Solvers

Automated configuration of mixed-integer programming (MIP) solvers largely relies on black-box optimization. Each trial requires an expensive solver run and provides only a scalar outcome, so tuning can require many such evaluations. Human…

Source: arXiv

ResearchOrdinary2026-10-31 12:41

Discovering Models for Experimental Quantum Systems with Agentic AI

A central obstacle in realizing color center cavity-QED-based quantum technologies is inhomogeneity, or disorder, among individual emitters. As the number of emitters increases, so does the complexity of the experimental data, making it di…

Source: arXiv

ResearchOrdinary2026-10-31 12:39

LM6-CastBench: A Geometry-Aware Simulation Dataset for Transient Thermal Prediction in LM6 Sand Casting

Transient thermal fields during solidification connect casting process conditions and cooling behaviour to the formation of defect-prone regions in aluminum cast ings. Repeatedly solving this thermal problem across geometries and process c…

Source: arXiv

ResearchOrdinary2026-10-31 12:33

Enhancing Language Model Reasoning with Structured Multi-Level Modeling

Inference-time scaling enhances a model's reasoning by extending its chain-of-thought (CoT). However, existing approaches typically rely on a single policy trained with outcome-reward reinforcement learning (RL), which often suffers from l…

Source: arXiv · DeepSeek

ResearchOrdinary2026-10-31 12:33

Learning from an Imitable Teacher: Competition Solution for the MetaFine Challenge

The MetaFine Open Competition (RoboFineMani workshop, CoRL 2026) evaluates fine-grained manipulation beyond binary success. Its five simulated tasks, from grasping a bottle by an instructed part to inserting letter-shaped pegs with 4 mm cl…

Source: arXiv

ResearchOrdinary2026-10-31 12:17

ECG2Gene: Deep Learning-Based Germline Tumor Susceptibility Gene Risk Assessment Using Electrocardiograms

Electrocardiograms (ECGs) may contain physiological information related to hereditary cancer susceptibility, but its relationship with future cancer risk remains unclear. Here, we present ECG2Gene, a two-stage deep-learning framework that …

Source: arXiv

TutorialsOrdinary2026-10-31 12:17

A Two-Line Function Caught AI Collusion Better Than the AI Did

A few days back, I took part in the Apart Research sprint where our team worked on the AI collusion...

Source: DEV Community

TutorialsOrdinary2026-10-31 12:15

Anthropic Automates Red-Teaming for Emergent Misalignment Research

Anthropic has published research showing how AI agents can automate parts of adversarial safety...

Source: DEV Community · Claude

ResearchOrdinary2026-10-31 12:14

Roz: A Taste Test for World Model Latents

State of the art latent dynamics world models achieve impressive performance for robot planning. But do they actually encode the physics of the world? In this paper, we show that popular world models today achieve strong results on tasks t…

Source: arXiv

ResearchOrdinary2026-10-31 12:13

Trail: Accurate Local Smart Home Control Using Decision Models

Natural-language driven smart home control remains challenging: cloud-hosted Large Language Models (LLMs) raise privacy concerns, while local Small Language Models (SLMs) can generate invalid actions or misinterpret requests. We introduce …

Source: arXiv · Qwen

ResearchOrdinary2026-10-31 12:09

Words Before Pixels: Selective Modality Routing for Vision-Language Model Unlearning

Vision-language model (VLM) unlearning is often treated as an objective-design problem: given multimodal forget data, the goal is to optimize a loss that removes undesirable behavior while preserving retained capabilities. We argue that th…

Source: arXiv

ResearchOrdinary2026-10-31 12:03

Sparse Autoencoder Attribution Graphs Are Decided at the Margin

Attribution graphs over the features of sparse autoencoders (SAEs) are used to predict what an ablation does and are compared across training seeds. A TopK SAE keeps the largest preactivations at each token, and a feature's margin is its p…

Source: arXiv

ResearchOrdinary2026-10-31 12:01

Conversational Interaction for LLM-Based Clinical Text-to-SQL: A User Study with Healthcare Professionals

Conversational text-to-SQL interfaces could give healthcare professionals natural-language access to electronic health record (EHR) data, but evidence for their real-world usability remains limited: prior evaluations have relied largely on…

Source: arXiv

ResearchOrdinary2026-10-31 11:56

Editing the Goal: Per-Token SAE Steering and Its Depth Limits in $π_{0.5}$

Sparse autoencoders (SAEs) have recovered interpretable, causally relevant features in robot foundation models (RFMs) such as $π_{0.5}$ (arXiv:2603.19183, arXiv:2603.19233). SAE features on individual instruction tokens are less interpreta…

Source: arXiv