AI on flights
I love that I get uninterrupted 4-16 hours on flights, which I mostly use to write future prompts and read past AI responses. I do miss AI on flights. But after installing Google Edge Gallery with Gemma-4-E2B-it (2.5GB) that runs on my mobile, I’ve solved a few practical problems. For example: I took a picture of a dish they served and asked: “Is this vegetarian?” (It was.) I asked, “Comics have text in panels, often written at the top in a box. Not the speech bubbles. It’s like a narrator or voice over. What are they called?” (Caption boxes.) “Summarize The Unbearable Lightness of Being. Why is it famous?” (Thoughtful, well-written novel on the choice vs commitment tradeoff.) It’s not a very smart model. It’s a bit slow. Transcription is average. It doesn’t run in the background. Only one chat at a time. No internet search, etc. ...