HN Explorer

fzysingularity

↗ HN profile [ 70.5 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Omnigent: Meta-Harness for Coding Agents (Claude Code, Codex, Cursor, Pi) (github.com)
    2 points 0
  2. 1 points 0
  3. DeepSeek OCR 2: Visual Causal Flow (huggingface.co)
    2 points 0
  4. Unified Vision-Language Agents – Detect, Segment, OCR, Generate and More (github.com)
    5 points 1
  5. VLM Showdown: GPT vs. Gemini vs. Claude vs. Orion (chat.vlm.run)
    15 points 1
  6. Show HN: Chat with Orion – a visual agent that sees, reasons and acts (chat.vlm.run)

    Hey HN! We’re excited to share Orion [1] — our new visual agent that sees, reasons, and acts across images, videos, and documents. Frontier VLMs (GPT, Claude, Gemini) can describe what they see, but they can’t reliably…

    22 points 9
  7. ChatGPT uses YOLOv8 to detect UI elements (twitter.com)
    1 points 0
  8. Build visual AI workflows from a prompt – OCR, detection, editing and more (colab.research.google.com)
    5 points 3
  9. How we solved multi-modal tool-calling in MCP agents – VLM Run MCP (docs.vlm.run)
    14 points 6
  10. 1 points 0
  11. video2json – Transcribe and analyze *hours-long* videos (docs.vlm.run)
    3 points 1
  12. Georgi Gerganov on X: "x2 speed for WASM by optimizing SIMD" / X (twitter.com)
    2 points 0
  13. I'm Hooked on Devin ( Cognition_labs) (twitter.com)
    1 points 0
  14. Ask HN: GPT4V and function calling use-cases

    Hi folks, What are some use cases of GPT4 Vision with function calling? Curious to hear what applications it potentially unlocks over the usual model with json mode.

    1 points 0
  15. Silent voice messages transcribe to "Thanks for watching" on ChatGPT (twitter.com)
    1 points 0
  16. Ask HN: What are people using to automatically catalog images/video today?
    1 points 0
  17. Ask HN: Which cloud provider offers AMD MI250/MI300?

    Anyone know of public clouds that offer access to AMD MI250/MI300s today? We're trying to run some @PyTorch benchmarks for our open-source inference server NOS (https://github.com/autonomi-ai/nos) and wanted to get a…

    2 points 5
  18. 1 points 0
  19. Serving LLMs on a Budget (docs.nos.run)
    2 points 0
  20. 2024 predictions on the open-source LLM wars (twitter.com)
    2 points 2
  21. Fly.io for Multi-Cloud?

    Is there something like fly.io for multi-cloud? I like fly’s deployment simplicity but don’t want to only rely on the fly network to deploy applications. Ideally something where I’m able to deploy ephemeral containers…

    1 points 1
  22. The AI Stack for the 3rd Epoch of Computing (spillai.substack.com)
    4 points 0
  23. My Own AI Server Cluster (erichartford.com)
    3 points 0
  24. AGI-pack: Dockerfile generator for ML developers (github.com)
    1 points 1
  25. Blog – Introducing Intrinsic Flowstate – Intrinsic (intrinsic.ai)
    1 points 0