vlm.run adds Image-in/Box-out to System One API, returning object coordinates in one call
spillai · x · 2026-10-22
vlm.run has added TypeSafe's native Image and Box support to its System One API: pass an image as the state, ask Box-typed questions, and get each object's region back as four normalized edges.
- One call can ask multiple targets (e.g. cat, plant, TV remote) and returns top/bottom/left/right coordinates for each
- Works with models like qwen/qwen3.8-27b via https://gateway.vlm.run/typesafe, using the same TypeSafe SDK
- Handy for lightweight visual grounding / detection-style engineering
More from coding & agent
- Migrating an entire Hermes automation workload to Antigravity took about 2 hours — rseroter · 2026-10-22
- How a second Mac mini lets AI agents auto-distribute compute-heavy tasks — tedddyoweh · 2026-10-22
- LangChain's Design Agent Shipped 3,000+ Assets and Earned 4.5M Views Since August — LangChain · 2026-10-22
- Databricks Chief AI Scientist: Evals Are the Biggest Bottleneck to Enterprise AI Adoption — jefrankle · 2026-10-22
- Developer plans a solar-aware job scheduler so his homelab rides free excess power — mertdumenci · 2026-10-22
- How do you design your agentic code review workflow? — lucasmeijer · 2026-10-22