Hacker News: cvamanhttps://news.ycombinator.com/user?id=cvamanHacker News RSShttps://hnrss.org/hnrss v2.1.1Wed, 22 Jul 2026 22:07:30 +0000<![CDATA[Show HN: Codex Micro on Your Phone]]>codex micro sold out, so i built one you can try on your phone

Comments URL: https://news.ycombinator.com/item?id=48995152

Points: 3

# Comments: 0

]]>Tue, 21 Jul 2026 17:09:39 +0000https://github.com/maxxspotter/codex-micro-appcvamanhttps://news.ycombinator.com/item?id=48995152https://news.ycombinator.com/item?id=48995152<![CDATA[New comment by cvaman in "Show HN: Codex Micro on Your Phone"]]>30-second demo: https://x.com/maxxspotter/status/2079303331046932678

]]>Mon, 20 Jul 2026 20:53:59 +0000https://news.ycombinator.com/item?id=48984746cvamanhttps://news.ycombinator.com/item?id=48984746https://news.ycombinator.com/item?id=48984746<![CDATA[Show HN: Codex Micro on Your Phone]]>Article URL: https://github.com/maxxspotter/codex-micro-app

Comments URL: https://news.ycombinator.com/item?id=48984742

Points: 2

# Comments: 1

]]>Mon, 20 Jul 2026 20:53:35 +0000https://github.com/maxxspotter/codex-micro-appcvamanhttps://news.ycombinator.com/item?id=48984742https://news.ycombinator.com/item?id=48984742<![CDATA[New comment by cvaman in "Fine-Tuning VLMs for Data Extraction"]]>Is it possible to host multiple fine-tuned VLMs on a single machine? like multiple models sharing the GPU(s) for inference?

]]>Fri, 04 Oct 2024 12:39:51 +0000https://news.ycombinator.com/item?id=41740777cvamanhttps://news.ycombinator.com/item?id=41740777https://news.ycombinator.com/item?id=41740777<![CDATA[New comment by cvaman in "Bridging Images and Text – A Survey of VLMs"]]>Curious to know if VLMs be adapted/extended for video-based tasks (generating video summaries, question answering from video...) by understanding interframe context and temporal dynamics?

]]>Tue, 17 Sep 2024 19:08:11 +0000https://news.ycombinator.com/item?id=41571466cvamanhttps://news.ycombinator.com/item?id=41571466https://news.ycombinator.com/item?id=41571466