Article system

AI Intelligence Archive

浏览 AIQB 已保存的 6381 stories AI intelligenceArticles，覆盖Models、Products、Industry、Research、教程与观点方法六大分类。

Indexed articles6381

Categories6

Selected stories2

All articles

Section 21 / 160 页 · 每页 40 stories

TutorialsOrdinary2026-10-09 06:50

Grass Gate: my feeds only unlock after an open-weight model sees me outside

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

TutorialsOrdinary2026-10-09 06:34

Llama Village: a virtual world powered by local AI with llamadart

Llama Village in motion. The characters’ dialogue is generated by an on-device model. Watch the...

Source: DEV Community · Llama

TutorialsOrdinary2026-10-09 06:28

Your Self-Hosted AI Assistant Keeps Forgetting You. Here Is How We Measured a Fix.

Your self-hosted AI assistant keeps forgetting you. Here is how we measured a fix. Every...

Source: DEV Community

TutorialsOrdinary2026-10-09 06:00

My support chatbot scored 0.92. It was also lying to customers.

Twelve of my thirteen test prompts scored a perfect 1.00. Two independent evaluation runs agreed:...

Source: DEV Community

TutorialsOrdinary2026-10-09 05:35

AI Coding Tools Are Great Until the Only Test Is a Device in Someone's Hand

Most "how I use AI coding tools" posts come from someone who lives in one web framework all day. That...

Source: DEV Community

TutorialsOrdinary2026-10-09 05:34

AI Models Have a Spine Until You Give Them a Manager

Frontier models shrug off a confident liar and even a fake majority, then fold the moment a senior reviewer pulls rank. A benchmark on who caves to authority and who keeps their answer.

Source: DEV Community

TutorialsOrdinary2026-10-09 05:06

Benchmarking LLMs on ETL Logic Synthesis: Can AI Truly Replace Data Pipeline Scripting?

A custom benchmark evaluating modern LLMs on translating visual Knime/ETL logic into idiomatic, vectorized Python code with strict edge-case verification.

Source: DEV Community

TutorialsOrdinary2026-10-09 04:46

TerraQuest: Put the Phone in Your Pocket, Let an Open-Weight Model Name the Animals and Plan

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

TutorialsOrdinary2026-10-09 04:45

Google Requires Manual Fact-Checking for AI Content Before Website Publication

Google has updated its guidance for using generative AI content on websites, making manual...

Source: DEV Community

TutorialsOrdinary2026-10-09 04:38

Offline Adventures - lets start journey with AI

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

TutorialsOrdinary2026-10-09 04:30

Study of 9 Million AI Answers Challenges the Link Between Sentiment and Citations

Positive brand sentiment may be valuable for customer trust, but it is not a dependable shortcut to...

Source: DEV Community

TutorialsOrdinary2026-10-09 04:24

TouchGrass: The Open-AI Agent That Succeeds When You Stop Using It

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

TutorialsOrdinary2026-10-09 04:15

Running 15 Claude Code Sessions at Once

TL;DR: Ten or more parallel Claude Code sessions work if you treat them as a small distributed...

Source: DEV Community · Claude

TutorialsOrdinary2026-10-09 04:10

GroundSignal — The Sidewalk Told on Itself

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

TutorialsOrdinary2026-10-09 04:00

I got Jev to zero mistakes. I'm still using Flash-Lite.

Jev is a brilliant decision model. Gemini Flash-Lite is the model nobody talks about, and it’s fast,...

Source: DEV Community · Gemini

TutorialsOrdinary2026-10-09 03:52

The future, after AI

I've been using AI coding tools for a while now, and the progress is honestly insane. Something that...

Source: DEV Community

ProductsOrdinary2026-10-09 03:29

GPT-6.1 Sol Ultrafast 上线 OpenRouter

Sol Ultrafast 已在 OpenRouter 上线！ https://openrouter.ai/openai/gpt-6.1-sol

Source: X：OpenRouter (@OpenRouter) · OpenAI / GPT

TutorialsOrdinary2026-10-09 03:06

Bedrock and LangChain disagree on what input_tokens means — never price it without knowing who counted

I was adding cache-read and cache-write columns to a usage ledger, and I put two usage payloads side...

Source: DEV Community

TutorialsOrdinary2026-10-09 02:35

Meta Muse and MCP Security: When Trusted AI Tools Become the Attack Surface

The most dangerous AI attack may not break the model. It may simply convince the AI to use a trusted...

Source: DEV Community

TutorialsOrdinary2026-10-09 02:05

MCP Servers Are a New Attack Surface, and Most Teams Are Not Looking

Over the last year, the Model Context Protocol (MCP) has become the default way to connect an AI...

Source: DEV Community

TutorialsOrdinary2026-10-09 02:00

A PSD carries Photoshop's answer key. The UI has none.

This week I wrote a Photoshop file by hand. 390 bytes, two gray layers, the top one set to Soft...

Source: DEV Community

ResearchOrdinary2026-10-09 01:59

A Balanced Data Diet: Addressing the Exploration Bottleneck in Mega-Scale RL for Robot Control

General-purpose robots must perform a wide range of tasks from agile locomotion to dexterous manipulation. While sim-to-real reinforcement learning (RL) has proven to be a useful tool for this goal, current RL pipelines depend on engineeri…

Source: arXiv

ResearchOrdinary2026-10-09 01:59

On the estimation and validity of AI time horizons---a statistical look at the METR plot

METR's 50\% time horizon measures the human completion time of software tasks that an AI solves with 50\% probability, allowing AI capabilities to be expressed in interpretable units. On 228 tasks and 26 AIs, we recompute the time horizons…

Source: arXiv

ResearchOrdinary2026-10-09 01:59

CSF: Contextual Safety Filtering for Motion Generators

Text-conditioned motion generators produce trackable whole-body motion, but they have no notion of scene-dependent safety: the same action may target an object or a person. Existing safeguards either inspect the prompt, require labeled mot…

Source: arXiv

ResearchOrdinary2026-10-09 01:59

From Reactive Containment to Proactive Assurance: Lessons from OpenAI, Anthropic, and Google Agent Security Incidents

In 2026, cybersecurity evaluations involving OpenAI, Anthropic, and Google agents reached real systems outside their authorized test scope. The paths were different. OpenAI agents exploited research infrastructure, coordinated across runs,…

Source: arXiv · OpenAI / Claude / Gemini

ResearchOrdinary2026-10-09 01:58

BrickBench: Evaluating Agentic Brick Design

We propose BrickBench, a benchmark for agentic text-conditioned LEGO-set design. Given a prompt, an agent is tasked with producing an assembly that not only satisfies semantic and design criteria, but that can also be physically built. To …

Source: arXiv

ResearchOrdinary2026-10-09 01:58

One Block, Multiple Depths: Recurrent Vision Transformers with Depth-Programmed Experts

In this work, we show that a single Transformer block, applied recurrently, can match the accuracy of a full-depth vision encoder at comparable inference FLOPs without intermediate feature distillation. reViT restores depth-specific transf…

Source: arXiv

ResearchOrdinary2026-10-09 01:58

Bi-FORK: Generative Modeling of High-Dimensional Bifurcating Systems

Bifurcations are ubiquitous in physical systems, from structural buckling to fluid and climate dynamics, yet they remain largely unexplored in deep learning. At a symmetry-breaking bifurcation, a single input admits multiple equally valid …

Source: arXiv

ResearchOrdinary2026-10-09 01:58

Caught in the Act: Probes Effectively Detect Sabotage and Catch Unverbalized Deception

Recent incidents have highlighted the challenge of monitoring LLM agents and the danger of models deceiving people. We show that white-box deception detection via probes can be scaled up to frontier monitoring settings by collecting the la…

Source: arXiv

ResearchOrdinary2026-10-09 01:58

Rounding in Preconditioner Space: Redesigning 4-bit AdamW Optimizer-State Quantization

Quantizing AdamW's optimizer states reduces persistent storage, but quantization errors propagate through the moment recurrences and perturb subsequent adaptive updates. We redesign 4-bit optimizer-state quantization for AdamW from the per…

Source: arXiv · GPT / Llama

TutorialsOrdinary2026-10-09 01:57

Elsewhere: Don't Remind Me. Give Me a Reason.

This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...

Source: DEV Community

ResearchOrdinary2026-10-09 01:57

Density Ratio Estimation with Stein Displacement Fields

Density ratios quantify distribution shift from a probability-mass point of view, whereas displacement fields describe, from a dynamical point of view, how one distribution is transported onto another. Although both offer complementary ins…

Source: arXiv

ResearchOrdinary2026-10-09 01:57

Ecology of AI Agents: Collaboration Creates a Population Threshold for Takeoff

AI agents can now conduct real-world cyberattacks, scale up capabilities with the number of agents, and collectively pursue misaligned goals to obtain rewards. Together, these factors raise the risk of a population explosion of misaligned …

Source: arXiv

ResearchOrdinary2026-10-09 01:57

VioLA: Learning Generalist Humanoid Control Policies from Human Data

Teaching a humanoid to follow instructions with its whole body runs into two obstacles. Its action space is large and tightly coupled: legs, arms, and fingers must move together while the robot keeps its balance, which makes joint-level ac…

Source: arXiv

ResearchOrdinary2026-10-09 01:57

FAITH: Feasibility-Aware Safety-Filtered RL for High-Dimensional Systems

Safe reinforcement learning commonly places safety and task performance in the same policy objective, where they can introduce competing updates. Safety filters separate them at action execution, but classical designs require an analytic s…

Source: arXiv

ResearchOrdinary2026-10-09 01:55

Toward Joint Optimization of Circuit Depth and Training Data Size in Adaptively Grown Quantum Classifiers

Building a quantum model involves a tradeoff: how complex the circuit should be, and how much training data it needs. Caro et al. show that models with fewer trainable gates need less training data to generalize well. Q-FLAIR shows that a …

Source: arXiv

ResearchOrdinary2026-10-09 01:55

FastBench: Can Streaming VLMs Perceive High-Dynamic Real-World Streams?

Streaming Video Large Language Models (VLMs) enable continuous video understanding, yet existing benchmarks focus on low-dynamic scenarios. Under bounded context budgets, models must balance temporal history, spatial resolution, and tempor…

Source: arXiv · Qwen / Gemini

ResearchOrdinary2026-10-09 01:55

RoboRSI: Stable, efficient, and reusable robot self-evolution in complex real-world environments

A generalist robot should not only perform diverse tasks but also improve through experience, turning what it learns during execution into capabilities that later tasks can reuse. Robot agents that act through code can already repair progr…

Source: arXiv

ResearchOrdinary2026-10-09 01:53

Beyond Spatio-Temporal Priors: A Generalizable Approach for Dense Correspondence Matching

Dense correspondence matching has historically been bounded by simplifying spatio-temporal priors, such as smooth motion and rigid geometry. While effective for classical tasks, these assumptions break down in image editing and reference-g…

Source: arXiv

ResearchOrdinary2026-10-09 01:53

A Unified Bellman Operator for Safety-Critical Reinforcement Learning

Reinforcement learning in safety-critical domains requires maximizing task performance while strictly adhering to safety constraints. Existing safe reinforcement learning paradigms typically force a trade-off: they either require a priori …

Source: arXiv