Top New Best Ask Show Jobs

ashu_trv

79 karma · joined September 5, 2016

Building @videodb_io I like building fundamental systems. Wanders in deep thoughts of technology, science, spirituality and human nature.

submissions comments

Search over the Visual World: off-the-shelf VLMs beat video embeddings

arxiv.org·6 pts·ashu_trv·

Record and Replay, teach AI agents desktop workflows by showing them once

github.com·1 pts·ashu_trv·

Show HN: Do Thought Streams Matter? A Benchmark of VLM Reasoning in Gemini 2.5

arxiv.org·3 pts·ashu_trv·

Show HN: I packaged decade of video infra battle scars into tools for AI agents

7 pts·ashu_trv·

Live video feed for every multimodal model not just Gemini

videodb.io·7 pts·ashu_trv·

Show HN: VideoDB – 80 % fewer hallucinations on NFL game analysis

docs.videodb.io·1 pts·ashu_trv·

Lessons Learned Building MCP for Video Infrastructure Startup

2 pts·ashu_trv·

Auto-Sync Your Docs, SDKs and Examples for LLMs and AI Agents

github.com·6 pts·ashu_trv·

Ask HN: Model to Analyse Financial Transactions

1 pts·ashu_trv·

Underwhelming MCP vs Hype

4 pts·ashu_trv·

Benchmarking vision-language models on OCR in dynamic video environments

arxiv.org·142 pts·ashu_trv·

Vision-Language Models vs. Traditional OCR in Video – New Benchmark

arxiv.org·6 pts·ashu_trv·

Show HN:Video is hard: until now

github.com·4 pts·ashu_trv·

Show HN: Instantly create video clips from LLM prompts

github.com·4 pts·ashu_trv·

Show HN: GPT-Powered Video Retrieval and Streaming

github.com·5 pts·ashu_trv·

Show HN: Twitter bot generates interactive transcript of any audio/video

twitter.com·7 pts·ashu_trv·