FreakyJolly: AI Tutorials, ComfyUI Workflows and Local AI Guides
LongCat-2.5 Open Weights: Meituan’s 1.6T MIT Model, Benchmarks, API Price and Hardware
Claude Sheets, Whiteboards and Meetings: What They Do, Plans and How to Use Them (2026)
ComfyUI API Guide: Run Workflows From Python (Prompt, WebSocket, Images)
LM Studio Not Loading Models? How to Fix “Failed to Load Model” and Search Errors
ComfyUI Inpainting Not Working? Every Cause and Fix (SD, SDXL and Flux Fill)
Seedream 5.5 Guide: 100-Round Editing, Transparent PNGs, Pricing and How to Use It (2026)
Claude Fable 5.2 and Mythos 5.2: Price, Benchmarks, Plan Access and How to Use Them (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
LongCat-2.5 Open Weights: Meituan’s 1.6T MIT Model, Benchmarks, API Price and Hardware
Meituan released LongCat-2.5 weights under MIT on 9 Nov 2026: 1.6T MoE, ~48B active, vision and video. Specs, vendor benchmarks, $0.30/$1.20 API, Claude Code setup and self-hosting needs.
The reading list
Latest stories
Claude Haiku 5.5 Guide: Pricing, Benchmarks, Rate Limits and When to Use It
Claude Haiku 5.5 costs $0.10/$0.50 per million tokens up to 100K, has 1M context and beats open-weight models on Artificial Analysis. Full…
GitHub Copilot in Xcode: Setup Guide for the Xcode 27.3 Coding Assistant
GitHub Copilot is now in Xcode’s coding assistant (public preview, Xcode 27.3 beta). Setup steps, features, plans, extension vs native, JetBrains Air.
Virtuals Protocol Explained: AI Agent Tokens, VIRTUAL and Risks (2026)
What Virtuals Protocol is, how AI agent tokens and the VIRTUAL token work, which chains it uses, the 2026 news, the risks,…
ChatGPT Memory Guide: Turn It On or Off, Edit, Delete and Temporary Chat
How ChatGPT memory works in 2026: saved memories, chat history, the Memory summary, deleting memories, Temporary Chat, Projects, plan limits and privacy.
How to Track and Cut Claude API Costs: Console, Spend Limits and Analytics API
Track Claude API spend by model, workspace, API key or person with the new Analytics API, set spend limits and alerts, and…
Gemini in Google Slides: How to Edit a Whole Deck, Create Slides and Images
Gemini in Google Slides can now edit a whole deck from one prompt. Plans, side panel steps, deck generation, images, themes, prompts…
Anthropic’s S-1 RSI Warning and METR’s 2x Finding, Explained
Anthropic’s S-1/A says it may soon cross its RSP threshold for AI-accelerated R&D. METR estimates a 2x speed-up. What both say and…
ChatGPT GIF Maker, Saved Reference Photos and Account Switching: How to Use Them
How to make GIFs in ChatGPT, save reference photos of people, pets and characters, delete them safely, and switch between two accounts…
Claude Message Threads API: How to Use It, Limits and Pricing
Claude message threads keep your conversation on the server so later requests send only new messages. How to use them, limits, pricing…
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.