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
AI Agents Now Run SETI’s Alien-Hunting Telescope: How It Works
AI agents now steer and analyse SETI’s Allen Telescope Array in real time on Nvidia GPUs. How the setup works, what it…
Claude Code Won’t Clone Existing Games Now: The New Opus 5.5 Rule Explained
Anthropic added a rule that stops Claude Code on Opus 5.5 from recreating existing games. What it says, what you can still…
Canva Layoffs 2026: 1,271 Roles Hit in a ‘Refounding’ (Was AI to Blame?)
Canva’s first mass layoff affects 1,271 roles (22%). What the CEO memo says, the AI angle, the severance package, and what it…
DeepSeek API Python Tutorial (2026): Models, Streaming, JSON, Tools and Errors
A complete DeepSeek API Python tutorial: API key, base_url, deepseek-flash vs v4-pro, streaming, thinking mode, JSON, tool calls, caching, off-peak and errors.
How to Block AI Crawlers in robots.txt (New AI Training Policy Token Guide)
The new __usage_ai-training robots.txt token lets you opt out of AI training at once. Every AI user agent, copy-paste rules, WordPress, Cloudflare,…
Claude Code Extension Backdoor on Cursor: How to Check, Clean Up and Harden
Claude Code extension 2.1.312 and 2.1.313 on Cursor planted an SSH backdoor. Check your version, clean up, rotate keys and harden auto-updates.
AGENTS.md Guide: Format, Example, Claude Code, Codex and Cursor Support
What AGENTS.md is, which coding agents read it (Codex, Cursor, Claude Code and more), a copyable example, monorepo setup and fixes when…
ASI Alliance (FET) Explained: Members, Merger, Ocean Exit and 2026 News
The ASI Alliance explained: Fetch.ai, SingularityNET and CUDOS, the FET merger history, Ocean’s exit, ASI-1 and ASI:One, 2026 news, risks and how…
MIT Used GPT-6 Astra to Edit Qwen’s Weights Directly: Math Score 7.9% to 48.1%
MIT researchers had GPT-6 Astra edit 0.016% of Qwen3.5-0.8B’s weights with no training, lifting MATH-500 from 7.9% to 48.1% by fixing a…
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.