# Bro Saw Two Photos and Made Up Lore > Source: > Published: 2026-10-12 02:58:54+00:00 *This is a submission for the [Hacktoberfest Open-Source AI Challenge Week 1: Touch Grass](https://dev.to/challenges/hacktoberfest-week1-2026-10-05)* Apparently, asking a 2B model for evidence was like asking a guy in a group chat for sources. I showed a small AI on my laptop two photos from a walk and asked how they were connected. It almost always had an answer. In 6 of my 10 test pairs, it invented the answer. So I changed the rules of my game: the AI can help you notice things, but it doesn't get to decide what's true. UNSEEN is a walking game. You start an expedition, put your phone away, walk, and come back with a photo of something you noticed. A local open-weight vision model describes what you see. Game rules, not the model, decide whether it counts. If it does, it earns materials for your virtual world. It's for people who like games but want a reason to look up. On my test walk, I spent 25 minutes outside and 2 minutes on the screen. **Go outside. Notice something real. Bring a piece of that discovery back to a world of your own.** [**Explore the Code**](https://github.com/urooj-vX/Unseen) • [** Quickstart**](https://github.com/urooj-vX/Unseen#13-getting-started) • [** Architecture**](https://github.com/urooj-vX/Unseen#9-architecture) • [** Evidence Gate**](https://github.com/urooj-vX/Unseen#7-how-the-evidence-gate-works) • **Test Results** Most digital games are closed loops. They reward you for sitting still, clicking faster, watching screens, and grinding synthetic numbers designed to keep your attention trapped inside an artificial box. **UNSEEN was built on an opposite conviction:** the most intricate, surprising, and grounding world ever made is the physical environment… Before building, I wrote a test and its pass bar: 10 photo pairs (6 related, 4 unrelated), run once through a small local model. The confidence was there. The receipts were not. | Check | Needed | Result | |---|---|---| | Good outputs | 6 / 10 | 2 / 10 | | Unrelated pairs answered "no relationship" | 6 / 7 | 1 / 7 | | Invented details stated as fact | at most 1 | 6 / 10 | | Median latency | under 30 s | 20.7 s (range 15.7-49.6 s) | The model failed my pass bar. Not a little. It had confidence, creativity, and absolutely no business handing out rewards. The latency numbers are not a clean benchmark because my laptop was swapping heavily. So the model no longer judges anything. It only describes the photo as structured data, and plain code decides: The evidence gate is deliberately boring; that's the point. It checks whether the observation contains the required evidence, whether the result is eligible, and whether that observation has already been claimed. It rejects ineligible or duplicate claims instead of letting the model award materials based on a plausible story. The model describes; deterministic code decides. Stack: Qwen3-VL-2B-Instruct (Q4_K_M) through Ollama, built with Antigravity. I could run the experiment myself. I could feed the model unrelated photos on purpose, read what it said, measure it, and redesign around the failures. With a hosted API, I would have had a black box and a bill. Inference here runs locally through Ollama, so photos aren't sent to a hosted AI service, and each photo costs nothing. A stronger hosted model might have judged relationships better, and this small one was slow on my hardware. Open-weight AI made the experiment possible. Careful engineering made the result trustworthy. Bro saw two photos and made up lore. This session shows how I traced UNSEEN's zero-reward bug to the evidence gate, fixed the classification logic, and verified the fix against live local inference. **Render**: [Try the UNSEEN frontend](https://unseen-013z.onrender.com/) Render hosts the shareable frontend; the vision model still runs locally through Ollama. The deployed frontend does not, by itself, provide a hosted inference service. The AI doesn't have to know everything. It just has to help us notice something worth going outside for. And when it doesn't know, "I don't know" is an honest answer.