visioninmyblood
- Karma
- 0
- Created
- ()
- Submissions
- 0
- Show HN: Visual Agents with Code Mode (vlm.run)
Rather than calling tools one by one, Orion 2 generates a program and runs it end to end, meaning fewer round-trips and lower latency. You can try it out at https://chat.vlm.run When orchestration is code, every…
- Mm-ctx – fast, multimodal context for agents (huggingface.co)
- Show HN: Visual Agents for Fitness: How to Enable Automated Exercise Feedback (jeremyparkphd.substack.com)
- Skild AI Raises $1.4B, Now Valued over $14B (businesswire.com)
- Why multimodal AI needs typed artifacts instead of ad-hoc URLs (joyous-screen-916297.framer.app)
- Gemini 3 Deep Think is here (gemini.google.com)
- Gaussian Splat Reconstruction from Anything via OpenAI Chat Completions (colab.research.google.com)
- Ghibli3D: Transform People into 3D Ghibli Characters (chat.vlm.run)
- Hunyuan 3D Engine Global (3d.hunyuanglobal.com)
- AI bots shake up hiring process (fortune.com)
- Orion: A Unified Visual Agent (arxiv.org)
- Nano Banana Pro Can Generate a Image from Lat Long (chat.vlm.run)