Testing AI Models: Eight of Them, One Kebab
Eight AI models, one silly question: why is a PommDöner better than a Lahmacun? This is how you find out which model convinces — and which just waffles.
Read more →Eight AI models, one silly question: why is a PommDöner better than a Lahmacun? This is how you find out which model convinces — and which just waffles.
Read more →A blog about AI, written with AI, stopped by an AI-tool update. The story of a small mishap — and what it reveals about AI tools.
Read more →Thinking Mode lets AI work through multiple reasoning paths before answering — fewer mistakes on complex tasks. Google's Deep Think is the newest example, and free options exist too.
Read more →In OpenWebUI you can build your own models: your system prompt, your LLM, your knowledge base — a personal AI assistant that doesn't need re-explaining every single time.
Read more →Elon Musk's rocket company is taking over AI coding assistant Cursor — the largest venture-backed startup acquisition in history. Here's what that means for you.
Read more →Everyone talks about ChatGPT and Claude from the US. Yet out of France comes an AI that's free, answers in a flash — and keeps your data in Europe.
Read more →Technically correct, practically useless — or dangerous. Two examples show why AI doesn't read between the lines when you leave something unsaid.
Read more →Gemini CLI was a beloved open-source AI tool with over 100,000 GitHub stars — now Google is pulling the plug. The replacement, Antigravity, has worse quotas and no open code.
Read more →A tool I used every day was shut down. The community rescued it as Zoo Code. What coding assistants can do, why open source comes with no eternity guarantee — and where token costs lurk.
Read more →Higgsfield generates professional AI videos from $15 — and quietly offers the infrastructure for a virtual influencer that runs around the clock. But what's really behind it?
Read more →