This test used a board image rendered from a known public FEN example, not a real user’s game photo. I tested it in TiinyOS with Qwen3.6-35B-A3B and reasoning on.
I wanted to know whether I could give TiinyOS a board image before asking about a chess position. I uploaded the PNG and asked for a square-by-square transcri
This is a test with a fictional subtitle snippet, run in TiinyOS using Qwen3.6-35B-A3B with reasoning on. It is not a test of video or transcription.
The line was short: “Is he keeping it?” I wrote a five-cue text subtitle snippet around it, with a red folder passed between characters, and tried two fresh TiinyOS chats.
I wanted to try the kind of search I'd use when I remember a picture but have no idea what the file is called.
I attached three real photos with plain filenames: IMG_001.jpg, IMG_002.jpg and IMG_003.jpg. The request was to find “the cat trying to fit into a cardboard box,” return the exact filename, and identify the mou
I wanted to know whether Tiiny could compare two documents that describe the same product from different angles, so I built a small test out of a PRD and a launch review for a fictional product, with deliberate disagreements planted in them. Both files stayed on my machine. I put them in a folder, pointed Tiiny at it,
By the end of the week, my notes were a mix of short updates, half-finished thoughts, and reminders. They named colleagues, staging access, legal wording that wasn't public yet, and finance numbers. I gave them to Tiiny and asked for a report on completed work, work in progress, problems, next week's priorities, and he
The representative quotes were the most useful part of this test. They gave me a quick way to check whether Tiiny’s conclusions matched what the customer had said.
The record was not a clean transcript. It was 58 minutes and roughly 5,800 words, mixing the customer’s answers with my questions, my notes, an observer’s no
