AIQB
Article system

AI Intelligence Archive

浏览 AIQB 已保存的 9756 stories AI intelligenceArticles，覆盖Models、Products、Industry、Research、教程与观点方法六大分类。

Indexed articles9756
Categories6
Selected stories2

All articles

Section 105 / 244 页 · 每页 40 stories

TutorialsOrdinary
Whistle: A 16.9 MB Speech-to-Text Model That Runs on Any CPU (Hands-On Test)
Say you set up your agent stack to accept voice notes, the way most voice-first projects start. The...
Source: DEV Community
TutorialsOrdinary
Claude Code Review in Production: How Our Review Rules Evolved Over Five Months
Claude Code review started at my company as a single prompt in a GitHub workflow, and five months...
Source: DEV Community · Claude
TutorialsOrdinary
Stop pasting other people's agent skills into your repo as-is
Agent skills (the SKILL.md files that Claude Code and Codex load) are easy to share, and GitHub is...
Source: DEV Community · Claude
TutorialsOrdinary
Steelmanning the case against on-chain AI verification
1/12 I get paid for work that an AI jury verifies on chain. That means I have every incentive to...
Source: DEV Community
ProductsOrdinary
fal 推出 Claude Motion 与 Claude Connector
Claude Motion 和 fal Claude Connector！ 在 YouTube 观看完整视频：https://youtu.be/dNFOJdE9Y3A?si=USRpKbwZXvhwZwfA
Source: X：fal (@fal) · Claude
ResearchOrdinary
腾讯混元发布 ExplorationBench 基准
more 🔛 https://github.com/Tencent-Hunyuan/ExplorationBench
Source: X：腾讯混元 (@TencentHunyuan)
TutorialsOrdinary
The F-160 Iron Rule: Why My AI Trading Bot Ignored a 75x Leveraged Meme Coin
The F-160 Iron Rule: Why My AI Trading Bot Ignored a 75x Leveraged Meme Coin It was 2:00...
Source: DEV Community
TutorialsOrdinary
With 160 skills installed, Claude Code kept 20 descriptions, and the model found 0 of 3 skills that lost theirs
With Opus 5.5's 1M-token window, Claude Code 2.1.289 held the skill listing to 30,000 characters. Of...
Source: DEV Community · Claude
TutorialsOrdinary
There's no fall foliage in Phnom Penh, so I built an offline AI that sends me out to flip buckets
MusPatrol (មូស Patrol): a 10-minute after-the-rain dengue patrol. CLIP names the container in your browser, a rules table decides what to do, and Gemma 4 is only allowed to narrate.
Source: DEV Community
TutorialsOrdinary
Your coding agent is following rules that are no longer true. Here is the fix.
AGENTS.md and CLAUDE.md go stale without throwing an error. It goes stale by design. Your agent will faithfully follow an old command that no longer exists. Here is a doc-drift check and a verify-by-retry loop that keeps the instructions h…
Source: DEV Community · Claude
TutorialsOrdinary
7 LLMs reconciled 73 Pix statements: 99.6% correct order links, zero invented orders observed, and the hard part was the clock
This is a submission for the Kaggle Benchmarking Challenge. What I Benchmarked Pix...
Source: DEV Community
ProductsOrdinary
Luma AI 推广试用 Luma 平台
试试 Luma - https://app.lumalabs.ai/?utm_source=x&utm_medium=p-social&utm_campaign=q4-brand&utm_content=leadershippov&utm_aud=plg
Source: X：Luma AI (@LumaLabsAI)
TutorialsOrdinary
Anthropic OSS Scanner Uses AI to Find Vulnerabilities in Opted-In Open-Source Projects
Anthropic has launched OSS Scanner, a free opt-in vulnerability-finding service for eligible...
Source: DEV Community · Claude
TutorialsOrdinary
Anthropic Launches Critical Infrastructure Defense Program for OT Security
Anthropic has launched the Critical Infrastructure Defense Program (CIDP), the flagship component of...
Source: DEV Community · Claude
TutorialsOrdinary
Anthropic Cyber Mission Expands AI Security Work for Infrastructure and Open Source
Anthropic has launched the Anthropic Cyber Mission, a long-term security initiative focused on two...
Source: DEV Community · Claude
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
GroundSignal — The Sidewalk Told on Itself
This is a submission for the Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass ...
Source: DEV Community
TutorialsOrdinary
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
TutorialsOrdinary
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
ProductsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
TutorialsOrdinary
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
ResearchOrdinary
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
ResearchOrdinary
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
ResearchOrdinary
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
ResearchOrdinary
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