FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
Grok API Watermark Is On by Default: Models, x-watermark Header and How to Opt Out (2026)
Run Qwen3.8-27B Locally in GitHub Copilot With Foundry Local (2026): 24 GB GPU Setup Guide
How to Tell if a Picture Is AI Generated: SynthID, Content Credentials and 6 Checks (2026)
How to Get Claude Pro for Free in 2026: Guest Passes, Students and Legit Ways
How to Move Ollama Models to Another Drive (Windows, Mac, Linux, Docker) 2026
How to Update ComfyUI Safely: Desktop, Portable and Git (Plus Uninstall) 2026
How to Stop Claude Saying Yes to Everything: Free Anti-Sycophancy Rule and Skill (2026)
Claude Duet Guide: How to Get Anthropic’s Proactive Agent, Setup, Limits and Safety (2026)
The world of AI. Explained.
A clearer view of artificial intelligence.
Hands-on guides for ComfyUI workflows, AI video, image editing and running models locally — tested, with every file path and setting written down.
- Lead story
Grok API Watermark Is On by Default: Models, x-watermark Header and How to Opt Out (2026)
Since 7 November 2026 the Grok API watermarks text from seven models by default. Which models, how it works, how to read the x-watermark header, how admins opt…
The reading list
Latest stories
Run Qwen3.8-27B Locally in GitHub Copilot With Foundry Local (2026): 24 GB GPU Setup Guide
Microsoft’s Foundry Local now runs a tuned 4-bit Qwen3.8-27B as a local coding agent inside GitHub Copilot. Specs, 24 GB GPU needs,…
How to Tell if a Picture Is AI Generated: SynthID, Content Credentials and 6 Checks (2026)
Check if an image is AI generated: Gemini’s SynthID check, Content Credentials (C2PA), reverse image search, metadata, AI detectors and visual clues,…
How to Get Claude Pro for Free in 2026: Guest Passes, Students and Legit Ways
Every legit way to get Claude Pro free in 2026: 7-day guest passes, Claude for Education, gift subscriptions, first-time promos, builder credits…
How to Move Ollama Models to Another Drive (Windows, Mac, Linux, Docker) 2026
Move Ollama models to another drive without re-downloading: default folders, the Model location setting, OLLAMA_MODELS on Windows, macOS and Linux, Docker volumes,…
How to Update ComfyUI Safely: Desktop, Portable and Git (Plus Uninstall) 2026
Update ComfyUI on Desktop, Portable or a Git install without breaking custom nodes: Stable vs Latest, updating nodes, rolling back a bad…
How to Stop Claude Saying Yes to Everything: Free Anti-Sycophancy Rule and Skill (2026)
Claude says “You’re absolutely right” and follows bad instructions? Here is why it happens and a free CLAUDE.md rule, goal-guard Skill and…
Claude Duet Guide: How to Get Anthropic’s Proactive Agent, Setup, Limits and Safety (2026)
Claude Duet watches your apps, sends a morning brief and works in the background. Who can get it, how to join the…
Microsoft’s AI Frontiers Lab Is Over and AutoGen Gets No Fixes: How to Migrate (2026)
Microsoft’s AI Frontiers lab has ended and AutoGen no longer gets bug or security fixes. Check which AutoGen you run and port…
TwIL-8B: Run webAI’s Small Maths and Code Reasoning Model Locally (Ollama, LM Studio, llama.cpp)
TwIL-8B is an 8.8B Granite-based reasoning model that rivals much bigger models on maths and code. Files, VRAM, Ollama and llama.cpp commands,…
How every guide is built
Copy the command. Drop the file. Run the graph.
Each ComfyUI guide follows the same shape, so you can skim straight to what you need.
- Step 1InstallNode packs and exact download commands.
- Step 2Files & pathsEvery model folder in one table.
- Step 3SettingsStarting values that work on consumer GPUs.
- Step 4TroubleshootKnown errors and the fix for each.
New models land fast. Get the working setup first.
Follow FreakyJolly in any feed reader to get every new guide the moment it goes live.