Subscribe
Sign in
Home
Start here
Local AI
Fixes & guides
Builds & gear
AI briefing
About
Walkthroughs
Latest
Top
Discussions
Qwen 3.5 vs the Desk Test: Why Local Coding Agents Still Fail
Why Qwen 3.5 looks strong in evals but breaks on your desk. A practical read on llama.cpp, tool calling, and local agent reliability.
Mar 21
•
Popular AI
1
ComfyUI Wan on RTX 3060: How to Cut 12GB GPU Render Times
Learn how to speed up Wan 2.1 image-to-video in ComfyUI on a 12GB GPU with better draft passes, TeaCache, and safer workflow choices.
Mar 19
•
Popular AI
1
1
Why ComfyUI updates break workflows and how to fix them
ComfyUI broken after an update? Learn what causes workflow failures and how to prevent node conflicts, UI bugs, and bad rollouts.
Mar 17
•
Popular AI
1
Why Ollama and llama.cpp crawl when models spill into RAM, and how to fix it
A practical guide to faster local AI: fit models in VRAM, tame context length, cut parallelism, and avoid silent CPU fallback.
Mar 16
•
Popular AI
1
Why long ChatGPT threads break down, and how to fix them
ChatGPT long threads are useful until they are not. Learn what causes context loss, browser lag, and model drift, plus how to prevent it.
Mar 14
•
Popular AI
1
1
How to Humanize AI Writing Before Readers Spot the Tells
AI writing has a measurable house style. Here’s how to remove the tells, protect your voice, and make generated prose feel human again.
Mar 8
•
Popular AI
2
How list formatting makes ChatGPT-style writing easy to spot
List formatting has become one of the clearest signs of AI writing. Here’s why readers notice it and how to prompt for cleaner prose.
Mar 7
•
Popular AI
1
1
How to free your AI writing from em dashes and punch-up punctuation
AI writing often leans on em dashes, stock contrast, and vague uplift. This guide shows how to clean it up before readers notice.
Mar 4
•
Popular AI
2
How to Stop ChatGPT From Writing “Not Just X, but Y”
Tired of “not only X, but Y” in AI copy? Use these prompt rules and revision steps to cut canned phrasing and improve readability fast.
Mar 3
•
Popular AI
1
1
ChatGPT’s ‘piss filter’: why AI images skew yellow (and how to fix it)
Is the warm hue of ChatGPT’s images proof of model collapse? A clear look at ChatGPT’s image pipeline, prompt rewriting, defaults, and quick fixes.
Mar 2
•
Popular AI
2
1
How Teachers Spot ChatGPT Essays Without a Detector
What makes AI-assisted essays stand out? The real giveaway is not a detector score. It is the language, structure, and missing authorial voice.
Feb 26
•
Popular AI
2
What is Docker and why should you use it?
“He who controls the environment controls the outcome.” — Every engineer who has ever wrestled with dependency hell
Aug 20, 2024
•
Ben Geudens
3
This site requires JavaScript to run correctly. Please
turn on JavaScript
or unblock scripts