7 minutes to master any new AI
Fresh, hands-on tutorials for every new AI release.
New model dropped? New tool launched? We test it, screenshot it, and turn it into a 7-minute guide you can actually use — never a press release rewrite.
Hand-tested by a builder · Live within 24h of every release · 272 guides & briefs shipped
Tutorials
view all →How to do it — we test each release and write the step-by-step guide you can follow.
-
Run Qwen3.6-35B-A3B Locally for Coding: llama.cpp, Quants & VRAM
Qwen3.6-35B-A3B activates just 3B params but scores 73.4% on SWE-bench Verified — and it runs on a 24GB GPU or a 32GB Mac. The exact llama.cpp setup, which quant to pick, the VRAM math, and how to wire it into a coding agent.
-
Fix llama-server 'Forcing Full Prompt Re-processing'
Seeing 'forcing full prompt re-processing due to lack of cache data' in llama-server? Fix SWA and KV-cache reuse with --swa-full, --cache-reuse and slot persistence.
-
Grok Build CLI: Install, Commands, and config.toml (the Practical Handbook)
The hands-on manual for xAI's grok CLI — installing a specific version (not just the latest), grok update, the slash commands that matter (/context, /compact, /fork, /rewind, /resume), where config.toml lives and the settings worth changing, and the full headless flag table for CI (-p, --output-format json, --max-turns, --allow/--deny, --sandbox). Every command is quoted from xAI's official user guide in the open-source repo.
-
llama-server Built-in Tools: Safe --tools all Setup with Docker
Use llama-server --tools all safely with a local GGUF. Set up read-only tools, Docker isolation via --tools-runtime, Web UI testing, and security guardrails.
-
How to Check and Patch Brotli CVE-2026-111497 (Decoder RCE) in Node.js, Bun, Envoy, Python and Linux
Practical response guide for CVE-2026-111497, the critical out-of-bounds write in Google's Brotli decoder found by OpenAI: which versions are fixed (Brotli 1.0.10/1.1.1/1.2.1, Node.js 22.23.4/24.22.1/26.12.1, Bun 1.4.4, Envoy 1.40.0+), how to find every copy on a host, why process.versions.brotli lies, and stopgaps if you can't upgrade today.
-
How to Deploy llm-d 1.0 on Kubernetes: Prefix-Cache-Aware vLLM Routing Step by Step
llm-d 1.0 is out with a v1 router config API, flow control and zero-downtime upgrades. Follow the official optimized-baseline path to put the llm-d Router in front of vLLM on Kubernetes, verify prefix-cache routing with real metrics, size it for fewer GPUs, and avoid the upgrade traps from 0.x.
Latest articles
The 48 newest tutorials and news. Tutorial archive · News archive
- Tutorial How to Check and Patch Brotli CVE-2026-111497 (Decoder RCE) in Node.js, Bun, Envoy, Python and Linux
- Tutorial How to Deploy llm-d 1.0 on Kubernetes: Prefix-Cache-Aware vLLM Routing Step by Step
- Tutorial How to Run Nemotron 3.5 Bolt E4B Locally: llama.cpp, DFlash and Ollama Setup
- Tutorial How to Use Kimi K3.1 Pro: API, Codex and Claude Code Setup, Pricing and Gotchas
- News Kimi K3.1 Pro arrives for coding agents — use the new model ID, but do not plan a local deployment yet
- Tutorial How to Check and Patch GitLab CVE-2026-110264 (CVSS 10 Unauthenticated RCE) on Self-Managed Instances
- Tutorial How to Lock Down Ollama, vLLM and llama.cpp Endpoints Against LLMjacking
- Tutorial How to Self-Host MiniMax M3.1 Flash with vLLM or SGLang: Hardware, Launch Commands and Fixes
- Tutorial How to Sandbox an AI Coding Agent with NVIDIA OpenShell: Install, Network Policy, First Agent
- Tutorial How to Set Up Replit Monitoring Agent: Alerts, Auto-fix, Auto-republish and Email Settings
- Tutorial How to Upgrade to TanStack AI 1.0: Streaming Chat, threadId, Codemod and Breaking Changes
- Tutorial How to Use the Kling 4.0 API on fal: Text, Image, Reference and Edit Endpoints, Pricing and Errors
- Tutorial How to Use the OpenAI Decisions API: First Request, Predicate/Choice/Score, Thresholds and Caching
- Tutorial How to Check and Patch PHP2Shell (CVE-2026-109618, CVE-2026-109619) on Your PHP Servers
- Tutorial How to Run Recursive Flint Locally: Ollama, rec on Mac, llama.cpp, and Coding Agent Setup
- Tutorial How to Set Up Claude Security Continuous Scanning (and the Claude Code Plugin Alternative)
- Tutorial How to Use the Mistral Large 4 API: Reasoning Effort, Tools, JSON Output, Caching and Batch
- News LiteLLM 1.107.0 shipped a credential stealer on PyPI and Docker: how to check and what to rotate
- News Railway says environment variables may have been decrypted: what to rotate while builds are paused
- Tutorial How to Install and Use the Official OpenAI CLI (v1.39): Setup, Responses, Files and Batches
- Tutorial How to Run DeepSeek-V4.1-Flash with DeepInfer: Build, Offline Inference, Parallelism, Structured Output
- Tutorial How to Run Pocket TTS Small Models on CPU: 18M, 7M and 1.9M Voice-Cloning TTS
- Tutorial How to Run PyTorch on Google Cloud TPUs with TorchTPU: Setup, torch.compile, Multi-Chip, Fixes
- Tutorial How to Use Local and Hosted LLMs in a Swift App with AnyLanguageModel 1.0
- News Perplexity Computer now runs fully local on Mac: Qwen 3.6 or PPLX Pro, 36 GB recommended
- Tutorial How to Build a Voice Agent That Never Goes Silent with Google ADK: Streaming and Non-Blocking Tools
- Tutorial How to Run Hugging Face Models on AWS Trainium with TorchNeuron: Install, Inference, Fine-Tuning, Errors
- Tutorial How to Run Ming-3.0-tts Locally: Clone Voices, Freeform Control, Paralinguistic Tags
- Tutorial How to Use Mercury 3, Inception's 1,000 tok/s Diffusion LLM: API, OpenRouter, Tools and Streaming
- Tutorial How to Use MiniMax M3.1 Flash: API Setup, Effort Levels, Tool Calls and Claude Code
- News DHS orders civilian agencies to remove DeepSeek, including third-party products built on it
- Tutorial How to Build Your First Browser Agent with Browser Use 0.13 in Python: Setup, Limits, Structured Output
- Tutorial How to Configure Claude Code Permissions: Auto Mode, Allow/Ask/Deny Rules, Sandbox and Team Lockdown
- Tutorial How to Forecast Time Series with Mistral Timestral on CPU: Install, Covariates, Quantiles, License
- Tutorial How to Switch to GPT-6.1 Sol (or Astra, Luna): Model IDs, Effort Settings, API and Codex Setup
- News Gemini Gems become skills from November: what migrates, what breaks, and how to move early
- News Google's Harness² auto-tunes agent prompts, skills and tools on OpenCode or Codex: how to run it
- News Agens Volundr 32B v1 on a 16 GB GPU: what the Agens Engine build needs, how fast it is, and what quality it gives up
- News Apple's RSI-Inference Bench: the best coding agent passes 26.7% of day-0 vLLM and SGLang model-support tasks
- News Claude Code is 3x faster to first token: what gzip and pre-started cloud sessions change, and when to set CLAUDE_CODE_GZIP_REQUEST_BODIES=0
- News Claude Design's standalone site closes December 14: how to migrate design systems, and what gets deleted
- News Claude Max and Team now include $100 to $500 a month in API credits: how to claim them, what they cover, and the one-link trap
- News Claude Opus 5.5 hands flagged cyber requests to Opus 4.8 — and Anthropic's own tests say that fallback is where prompt injections land
- News Codex desktop app filling your Mac's disk? Check Crashpad/pending — where the dumps live, how to clear them, and what OpenAI hasn't fixed yet
- News DeepSeek-V4.1-Flash-1017 on one 128 GB Mac: a ds4 Q2 GGUF is out, but vision waits on PR #1225
- News Elorian Glimpse: a $0.60/$3 visual-reasoning API that beats GPT-6 Astra on video captioning — and where it still trails
- News Granite Switch 4.1: serve chat, decisions, and speech from one vLLM endpoint — and pin the right vLLM
- News JetBrains Mellum2.1 Thinking locally: 7–13 GB GGUF builds, llama.cpp and vLLM commands, and where the 12B MoE falls short