AI tools
From glossary entries and tool comparisons to coding agents and local models: every step of putting AI to work, written to be followed.
Series and tutorial hubs
Series to read in order, each with its own directory and learning paths.
Codex learning hub: tutorial directory
A planned 60-lesson, ten-unit Codex curriculum, from setup and your first task to MD instructions and advanced integrations. Find your next lesson by experience, platform, goal or command; unpublished entries show their status.
Start from what you need
AI news
See allAI images, video & audio
See all
Lifestyle
Using AI for UI Design: From Requirements in Prompts to Verifiable Interfaces
AI-assisted UI design needs more than detailed prompts: link requirements, assumptions and acceptance checks. An original laundry status lookup page shows what context to supply, screen states, edit scope and data boundaries. A comparison table, steps and original diagram explain checks of content, keyboard use and user tasks, helping everyday users turn generated drafts into interfaces they can discuss and test, without treating simulated responses as real research.
- AI tools
- Tutorials
- AI images, video & audio
Lifestyle
Claude Code 2.1.330: Enterprise Admin Console Sign-In, easel Chart Module, and Scheduled Tasks Extended to 30 Days
Anthropic's Claude Code 2.1.330 changelog lists Enterprise Admin Console sign-in, a built-in easel chart module, scheduled tasks of up to 30 days, and stricter approval for rm commands.
- AI news
Lifestyle
AWS Quick adds chat-built flows, multi-agent answers and Meta ads/Amplitude connectors, available today in all Quick regions
AWS has updated AWS Quick with chat-based flow building, an updated web app, multi-agent collaboration and new connectors. AWS says the features are available today in all regions where Quick is offered. Prompt guardrails are in preview, and some admin features are limited to Professional and Enterprise plans.
- AI news
Lifestyle
AWS Distributed KV Caching Agent Skill for Self-Hosted LLMs: AWS Says Cost Drops Up to 40% and Time to First Token Up to 80%
AWS offers a distributed KV caching skill in the Agent Toolkit for AWS, letting coding agents such as Kiro and Claude Code help assess, build and debug a shared cache for self-hosted LLMs. AWS says costs fall up to 40% and time to first token up to 80%, with GPU and software version prerequisites.
- AI news
Lifestyle
Amazon SageMaker HyperPod Slurm Adds Cluster Extensions: Managed Observability and User Management, Available in All HyperPod Regions
AWS has introduced cluster extensions for SageMaker HyperPod Slurm clusters, starting with two managed extensions for observability and user management, manageable via API or console. Per AWS, there is no extra charge, but AMI and continuous provisioning requirements apply.
- AI news
Lifestyle
Amazon Textract Insights Now Generally Available: Extract Document Fields in Natural Language, With Confidence Scores and Page Grounding, Up to 3,000 Pages per File
AWS announced general availability of Amazon Textract Insights, which lets you define fields in natural language and process mixed document packets, with a confidence score and page grounding for each value. It supports six languages, and is not yet available in Tokyo or Zurich.
- AI news
Lifestyle
Inkling 2 Mini: A Local Multimodal MoE Model with About 26B Parameters (3B Active per Token), Supporting transformers, llama.cpp and MLX
On November 20, Hugging Face introduced Inkling 2 Mini from Thinking Machines Lab. It is a multimodal looped MoE model built to run locally, with support for transformers, llama.cpp, MLX and SGLang.
- AI news
Lifestyle
Replit Tunnels: Enterprises Can Connect Replit to Private-Network Databases and Internal APIs via an IT-Run Client (Early Access)
Replit has announced Tunnels, which lets enterprise Replit environments reach private services through a client that IT runs inside the internal network. For now, early access requires contacting Replit.
- AI news
Lifestyle
Trump Threatens 'Tremendous Tax' on US Firms Building Data Centers Abroad: Verbal Pledge Only, No Rate or Timeline
The Verge reports that Trump said at a press conference he would put a 'tremendous tax' on companies that build data centers outside the US. He gave no rate, scope or timeline, so for now it is a verbal statement, not a policy in force.
- AI news
Lifestyle
Google Launches Connected Apps in the US for Search and Gemini: Target, Experian, H&R Block and More
Google announced new Connected Apps in the US across Search and the Gemini app, covering grocery ordering, credit and loans, and tax estimates, with Angi and Thumbtack coming in the next few weeks.
- AI news
Lifestyle
Google Cloud Managed Airflow adds AI agents for debugging, upgrade checks and DAG writing; its MCP server is now generally available
Google Cloud says Managed Airflow now offers AI agent help across the pipeline lifecycle, including the Managed Airflow Agent in the console and the Data Agent Kit in the IDE; its MCP server is now generally available.
- AI news
Lifestyle
Senate Passes DEATH BETS Act: Bill Would Ban War, Terrorism, Assassination and Death Contracts on CFTC-Regulated Platforms, House Vote Still Needed
Decrypt reports the US Senate passed the amended DEATH BETS Act by voice vote on Nov. 19. It would bar CFTC-regulated platforms from listing war, terrorism, assassination and death event contracts. The House must still pass it; it is not yet law.
- AI news
Lifestyle
Hugging Face Publishes Harness Adapters Recipe: Qwen3.8-27B Rises from 39.2% to 64.7% on SWE-bench Pro with pi
Hugging Face describes harness adapters: LoRAs trained with RL inside the target agent harness. Qwen3.8-27B gains accuracy and makes fewer tool calls. Recipe and artifacts are public, but results are self-evaluated.
- AI news
Lifestyle
Signal Blocks Screenshots by Default on Android and iOS 27 to Stop AI Agents Like Siri and Gemini From Reading Your Screen
The Verge reports that Signal is restricting screenshots on Android and iOS 27 to keep OS-level AI agents from reading message content. Users can turn screenshots back on in settings, but Signal warns this weakens its privacy protections.
- AI news
Lifestyle
Claude Code 2.1.329: Code Mode Works With Telemetry, /tasks Lists Scheduled Tasks, macOS Computer Use Gets Stricter Safety Rules
Anthropic's changelog lists Claude Code 2.1.329, covering Code Mode behavior changes, new diagnostics in /tasks and /mcp, /code-review changes, and new safety rules for macOS computer use.
- AI news
Lifestyle
Kimi Code CLI v2.7.0 Adds a Native Amazon Bedrock Provider: Use Your AWS Credentials Instead of a Separate API Key
AWS says Moonshot AI added a native bedrock provider in Kimi Code CLI v2.7.0, letting you call Amazon Bedrock models with the AWS credential chain (including named profiles and SSO) without managing separate Bedrock API keys.
- AI news
Lifestyle
AWS Rounds Up 13 SageMaker Inference Features: Managed NVIDIA Dynamo on HyperPod, MIG GPU Partitioning, Cross-Region Routing
On November 20, AWS published part 2 of its 2026 SageMaker Inference review, covering 13 post-launch operations features across recommendations, GPU partitioning, large-model serving, cross-Region routing and monitoring.
- AI news
Lifestyle
BMW Group Shares How It Governs AI Agents: 12,500+ Developers, Three Autonomy Levels and a Four-Stage CI/CD Gate
An AWS blog post describes how BMW Group governs hundreds of AI agents using three autonomy levels, deterministic CI/CD checks and a central registry. It shares architecture practices; it is not a new product you can buy or download.
- AI news
Lifestyle
Amazon SageMaker AI Now Monitors vLLM GPU Inference Endpoints by Default: Latency Drift, Idle GPUs and Missed Optimizations
AWS announced that SageMaker AI now monitors generative AI inference endpoints running vLLM containers on GPU instances by default, sending AWS Health notifications about latency, idle capacity and configuration issues without automatically changing production.
- AI news
Lifestyle
Gemini Can Now Import Your Preferences and Chat History From Other AI Assistants via a Prompt and a ZIP Upload
In a November 19 post, Google explains that users can generate a preferences summary with a prompt and upload a ZIP of chat history exported from a previous service to bring their data into Gemini. The post does not state supported plans or regions.
- AI news
Lifestyle
Google Search Homepage Adds a Sidebar to View and Continue AI Mode Chats, Rolling Out on Desktop Worldwide
According to The Verge, Google has added a collapsible sidebar to its search homepage that lists your AI Mode searches and lets you continue those conversations. It is rolling out on desktop worldwide.
- AI news
Lifestyle
Amazon Bedrock AgentCore harness adopts the Strands harness: new built-in tools and 4 lifecycle hooks, rolling out from November 11
AWS says Amazon Bedrock AgentCore harness now uses the open-source Strands harness defaults, with new built-in tools and lifecycle hooks. Existing harnesses get them automatically; explicit settings stay unchanged.
- AI news
Lifestyle
Amazon Polly Voice Cloning Now Generally Available: 7 Languages, Free Voice Creation, Access by Request
AWS announced that Amazon Polly voice cloning is generally available as a gated release. It supports 7 languages, voice creation is free and usage is pay-as-you-go. Access is enabled per account; request it through your AWS account team or the request page.
- AI news
Lifestyle
Anthropic Commits 5% of Its Shares to a Public Benefit Fund, With 2% More per 50% Value Gain; TechCrunch Estimates About $156 Billion in Potential Giving
Anthropic announced a Public Benefit Fund and, subject to shareholder approval, committed 5% of its shares, with more possible as company value grows. TechCrunch separately estimates potential giving of about $156 billion including employee matching, with several caveats.
- AI news
Lifestyle
Skyflow Interceptor on Amazon Bedrock AgentCore Gateway: Three Modes to Protect Agent Tool Calls, Document Feature in Preview
An AWS blog explains how the Skyflow interceptor attaches to AgentCore Gateway to de-identify agent tool calls; string handling is generally available, while document handling (Detect v2) is still in preview.
- AI news