HN Explorer

ashu_trv

↗ HN profile [ 57.0 ms ] full profile
Karma
0
Created
()
Submissions
0
  1. Record and Replay, teach AI agents desktop workflows by showing them once (github.com)
    1 points 0
  2. Show HN: Do Thought Streams Matter? A Benchmark of VLM Reasoning in Gemini 2.5 (arxiv.org)
    3 points 1
  3. Show HN: I packaged decade of video infra battle scars into tools for AI agents

    Hi HN, I’m Ashu, founder of VideoDB. I’ve spent a big chunk of my life building video infrastructure. Not video creation. Video plumbing. The stuff you only learn after production breaks: timebases, VFR, keyframes,…

    7 points 0
  4. 1 points 0
  5. 1 points 0
  6. Live video feed for every multimodal model not just Gemini (videodb.io)
    7 points 2
  7. Show HN: VideoDB – 80 % fewer hallucinations on NFL game analysis (docs.videodb.io)
    1 points 0
  8. 1 points 0
  9. Lessons Learned Building MCP for Video Infrastructure Startup

    Hey HN, We've been deeply immersed in building chat-based video interactions for nearly two years. We recently launched VideoDB MCP as a practical exploration of MCP capabilities, and while there's plenty we're excited…

    2 points 0
  10. Auto-Sync Your Docs, SDKs and Examples for LLMs and AI Agents (github.com)
    6 points 3
  11. Ask HN: Model to Analyse Financial Transactions

    Are there any good product, LLMs or models to analyse financial transactions? Looking for local tools or models.

    1 points 1
  12. Underwhelming MCP vs Hype

    My early thoughts on MCPs : As I see the current state of hype, the experience is underwhelming: Confusing targeting — developers and non devs both. For devs — it’s straightforward coding agent basically just llm.txt ,…

    4 points 20
  13. Benchmarking vision-language models on OCR in dynamic video environments (arxiv.org)
    123 points 59
  14. Vision-Language Models vs. Traditional OCR in Video – New Benchmark (arxiv.org)
    6 points 1
  15. Show HN:Video is hard: until now (github.com)
    4 points 4
  16. Show HN: Instantly create video clips from LLM prompts (github.com)
    4 points 5
  17. Show HN: GPT-Powered Video Retrieval and Streaming (github.com)
    5 points 1
  18. Show HN: Twitter bot generates interactive transcript of any audio/video (twitter.com)
    7 points 2