| 1. | | Show HN: Do Thought Streams Matter? A Benchmark of VLM Reasoning in Gemini 2.5 (arxiv.org) |
| 3 points by ashu_trv 50 days ago | past |
|
| 2. | | Show HN: I packaged decade of video infra battle scars into tools for AI agents |
| 7 points by ashu_trv 3 months ago | past |
|
| 3. | | Live video feed for every multimodal model not just Gemini (videodb.io) |
| 7 points by ashu_trv on May 30, 2025 | past | 2 comments |
|
| 4. | | Show HN: VideoDB – 80 % fewer hallucinations on NFL game analysis (videodb.io) |
| 1 point by ashu_trv on April 30, 2025 | past |
|
| 5. | | Lessons Learned Building MCP for Video Infrastructure Startup |
| 2 points by ashu_trv on April 10, 2025 | past |
|
| 6. | | Auto-Sync Your Docs, SDKs and Examples for LLMs and AI Agents (github.com/video-db) |
| 6 points by ashu_trv on April 7, 2025 | past | 3 comments |
|
| 7. | | Ask HN: Model to Analyse Financial Transactions |
| 1 point by ashu_trv on March 24, 2025 | past | 1 comment |
|
| 8. | | Underwhelming MCP vs Hype |
| 4 points by ashu_trv on March 17, 2025 | past | 10 comments |
|
| 9. | | Benchmarking vision-language models on OCR in dynamic video environments (arxiv.org) |
| 142 points by ashu_trv on Feb 14, 2025 | past | 58 comments |
|
| 10. | | Vision-Language Models vs. Traditional OCR in Video – New Benchmark (arxiv.org) |
| 6 points by ashu_trv on Feb 13, 2025 | past | 1 comment |
|
| 11. | | Show HN:Video is hard: until now (github.com/video-db) |
| 4 points by ashu_trv on Dec 4, 2024 | past | 4 comments |
|
| 12. | | Show HN: Instantly create video clips from LLM prompts (github.com/video-db) |
| 4 points by ashu_trv on Feb 23, 2024 | past | 5 comments |
|
| 13. | | Show HN: GPT-Powered Video Retrieval and Streaming (github.com/video-db) |
| 5 points by ashu_trv on Feb 8, 2024 | past | 1 comment |
|
| 14. | | Show HN: Twitter bot generates interactive transcript of any audio/video (twitter.com/spext_it) |
| 7 points by ashu_trv on July 28, 2020 | past | 2 comments |
|
