Search San Francisco using natural language
Hey HN! We're Alex and Szymon from Bluesight (https://bluesight.ai/), where we're developing a foundation model for satellite data. We've created a demo to showcase the current capabilities of state-of-the-art models and identify areas for improvement. Our demo allows you to search for objects in San Francisco using natural language. You can look for things like Tesla cars, dry patches, boats, and more. Key features: - Search using text or by selecting an object from the image as a source ("aim" icon) - Toggle between object search (default) and tile search ("big" toggle,…
In plain words
Search San Francisco using natural language is a demo tool that lets users search satellite imagery of San Francisco by describing what they want to find. Users can enter text queries like "Tesla cars" or "boats," or select objects directly from images. The tool toggles between object and tile search modes, includes a map locator, and uses voting to refine results. It showcases capabilities of foundation models applied to satellite data.
written from the facts on this page · September 2026
From the sources
In the maker’s words, at launch
Hey HN! We're Alex and Szymon from Bluesight (https://bluesight.ai/), where we're developing a foundation model for satellite data. We've created a demo to showcase the current capabilities of state-of-the-art models and identify areas for improvement. Our demo allows you to search for objects in San Francisco using natural language. You can look for things like Tesla cars, dry patches, boats, and more. Key features: - Search using text or by selecting an object from the image as a source ("aim" icon) - Toggle between object search (default) and tile search ("big" toggle, useful when contextual information matters, like tennis courts) - Adjust results with downvotes (useful when results are water images) - Click on tiles to locate them on a map - Control the number of retrieved tiles with a slider We use OpenAI's CLIP model (https://openai.com/index/clip/) to put texts and images into the same embedding space. We do a similarity search within this space using text query or source image. We are using CLIP finetuned on pairs of satellite images and OpenStreetMap (https://www.openstreetmap.org/) tags (https://github.com/wangzhecheng/SkyScript) because vanilla clip performs poorly on satellite data. We pre-segment objects using Meta's Segment Anything Model (https://segment-anything.com/) and pre-compute CLIP embeddings for each object. We'd love to hear your thoughts! What worked well for you? Where did it fail? What features do you wish it had? Any real-world problems you think this could help with?
More ai this month
the category →
I trained a 125M-parameter transformer to autocomplete piano performances in real time (~108 notes/sec on an iPhone 15). The idea is basically GitHub Copilot or Tabnine, except instead of prompting it with code, you prompt it by playing a few notes on a MIDI piano. The model then continues what you played, entirely on-device. The app is free if anyone wants to try it. Happy to answer questions about the model, training, Core ML, or the many things that didn't work.
AI · 17d ago · simedw.com
Astute▲585Automate your B2B brand going viral, with new media creators
AI · 18d ago · company-app.joinastute.com
Hey HN, Henry from Cactus here! We previously released Cactus Needle, a 14MB agentic LLM for tool call, device use, and structured extraction for phones, wearables, smart homes, small robots and microcontrollers. We got really great feedback here, and have now incorporated the suggestions to release Needle 2. The whole model is a single 14MB binary that runs a full session in 28MB of RAM; 45m parameters at 2bit compression. Needle hits 500 tokens/sec decode speed on a Raspberry Pi 5, sits between 400-1,500 tokens/sec on VR devices like Meta Quest 3S and Apple Vision Pro, and ranges…
AI · 27d ago · cactuscompute.com
Launched alongside, September 2024
the whole month →
BeforeSunset AI 2.0▲1,267Personalized AI daily planning that suits your life
AI · 2024 · beforesunset.ai
