Daily(ish) GenAI
Experiments

Testing AI tools on real tasks and sharing what actually happens

Welcome

A starting point for anyone curious about AI tools but not sure where to begin or what to believe.

Every day (or close to it), these experiments test AI tools on real tasks that matter to real people. Not to showcase flashy capabilities or sell you on the latest tech, but to give you an honest understanding of what these tools can actually do versus what they claim to do.

What You'll Find Here

Practical experiments that attempt to answer many of the questions you're probably asking:

  • Will this actually save me time?
  • Can I trust the output?
  • Is it worth learning a new tool for this?
  • What happens when things go wrong?

Each experiment documents the complete journey, from the initial setup (which is often half the battle) to the final results. You'll see both the wins and the failures, because understanding limitations is just as important as discovering capabilities.

Browse by Tag

Tools Tested

ChatGPT, Claude, Gemini, Midjourney, DALL-E, Runway, NotebookLM, Perplexity, and more...

Get Experiment Updates

Subscribe to receive new experiments and honest AI tool reviews delivered to your inbox.

Don't have a LinkedIn account? Subscribe here and I'll send you a link when I publish a new experiment.