Hacker News: visioninmyblood

Show HN: Visual Agents with Code Mode

visioninmyblood — Wed, 17 Jun 2026 18:30:07 +0000

Rather than calling tools one by one, Orion 2 generates a program and runs it end to end, meaning fewer round-trips and lower latency. You can try it out at https://chat.vlm.run

When orchestration is code, every workflow is composable, inspectable, and deterministic.

We put together a short Orion 2 demo video: https://www.youtube.com/watch?v=rzhXcNAYQ-0

Comments URL: https://news.ycombinator.com/item?id=48574623

Points: 8

# Comments: 1

New comment by visioninmyblood in "Mm-ctx – fast, multimodal context for agents"

visioninmyblood — Tue, 12 May 2026 22:08:54 +0000

LLM-based agents handle text incredibly well, but images, videos, or PDFs with visual content are hard to interpret. mm-ctx gives your CLI agent multi-modal skills.

Try it interactively in Spaces: vlm-run/mm-ctx

Readme: https://vlm-run.github.io/mm/ PyPI: https://pypi.org/project/mm-ctx SKILL.md: https://github.com/vlm-run/skills/blob/main/skills/mm-cli-sk...

mm-ctx is meant to feel familiar: the UNIX tools we already love (find/cat/grep/wc), rebuilt for file types LLMs can't read natively and designed to work with agents via the CLI. - mm grep "invoice #1234" ~/Downloads searches across PDFs and returns line-numbered matches - mm cat .pdf returns a metadata description of the file - mm cat .jpg returns a caption of the photo - mm cat .mp4 returns a caption of the video

A few things we obsessed over: Speed: Rust core for the hot paths Local-first, BYO model: Uses any OpenAI-compatible endpoint: Ollama, vLLM/SGLang, LMStudio with any multimodal LLM (Gemma4, Qwen3.5, GLM-4.6V). Composable: stdin + structured outputs Drops into any agent via mm-cli-skills: Claude Code, Codex, Gemini CLI, OpenClaw.

We’d love to hear your feedback! Especially on the CLI and what file types and workflows you would like to see next.

Mm-ctx – fast, multimodal context for agents

visioninmyblood — Tue, 12 May 2026 22:08:54 +0000

Article URL: https://huggingface.co/posts/spillai/891696740911772

Comments URL: https://news.ycombinator.com/item?id=48115253

Points: 2

# Comments: 1

New comment by visioninmyblood in "Muse Spark: Scaling towards personal superintelligence"

visioninmyblood — Wed, 08 Apr 2026 16:43:24 +0000

https://meta.ai/ this is where you can try it seems like the API is not publicly accessable yet. I feel they are very late to the game and do not show value to customers over other models.

Show HN: Visual Agents for Fitness: How to Enable Automated Exercise Feedback

visioninmyblood — Thu, 26 Feb 2026 22:24:47 +0000

Article URL: https://jeremyparkphd.substack.com/p/daaee5d4-9fd9-40a4-8d03-19cf298c57dc

Comments URL: https://news.ycombinator.com/item?id=47172864

Points: 3

# Comments: 0

New comment by visioninmyblood in "Ask HN: Who is hiring? (February 2026)"

visioninmyblood — Mon, 02 Feb 2026 21:03:19 +0000

The roles seems more oriented towards visual agents. Is this is similar to google vision agent but with more capabilities?

Skild AI Raises $1.4B, Now Valued over $14B

visioninmyblood — Wed, 14 Jan 2026 20:45:08 +0000

Article URL: https://www.businesswire.com/news/home/20260114335623/en/Skild-AI-Raises-%241.4B-Now-Valued-Over-%2414B

Comments URL: https://news.ycombinator.com/item?id=46623032

Points: 1

# Comments: 0

New comment by visioninmyblood in "[dead]"

visioninmyblood — Tue, 06 Jan 2026 20:19:30 +0000

Blog: https://vlm.run/blog/introducing-orion-artifacts

Cookbook: https://github.com/vlm-run/vlmrun-cookbook

Docs: https://docs.vlm.run/agents/artifacts

New comment by visioninmyblood in "Why multimodal AI needs typed artifacts instead of ad-hoc URLs"

visioninmyblood — Tue, 06 Jan 2026 19:59:40 +0000

Blog: https://vlm.run/blog/introducing-orion-artifacts

Cookbook: https://github.com/vlm-run/vlmrun-cookbook

Docs: https://docs.vlm.run/agents/artifacts

Why multimodal AI needs typed artifacts instead of ad-hoc URLs

visioninmyblood — Tue, 06 Jan 2026 19:59:40 +0000

Article URL: https://joyous-screen-916297.framer.app/blog/introducing-orion-artifacts

Comments URL: https://news.ycombinator.com/item?id=46517772

Points: 2

# Comments: 1

New comment by visioninmyblood in "ManusAI Joins Meta"

visioninmyblood — Mon, 29 Dec 2025 23:10:28 +0000

Meta was lacking behind on the agents space. This is a good capture but they are making crazy good offers but not turning them into killer products so far. The AI agents space is picking up in 20206. Next they will hire voice agents like ElevenLabs and Cartesia, visual Agents like VLM Run or Landing AI and then web browsing agents.

New comment by visioninmyblood in "TRELLIS.2: state-of-the-art large 3D generative model (4B)"

visioninmyblood — Sat, 20 Dec 2025 03:09:19 +0000

was fun generating the as well

New comment by visioninmyblood in "TRELLIS.2: state-of-the-art large 3D generative model (4B)"

visioninmyblood — Thu, 18 Dec 2025 21:16:38 +0000

you can chat with vlm.run to generate these assets from image generation without needing a gpu.

Modi: https://chat.vlm.run/c/bdbaf1dc-b3c2-4b8a-ad17-6e26d87475fd

Musk: https://chat.vlm.run/c/894f44ce-c366-4c93-b348-de6eebfb9f03

Ronaldo: https://chat.vlm.run/c/db5eff27-8c52-4e0b-8e4e-157df6bef278

Gomez: https://chat.vlm.run/c/02b92f23-a6fd-4380-b7a9-52ae7463c9c1

Jackie chan: https://chat.vlm.run/c/62ca5502-2066-4d5f-b994-c8845b2e72c9

Messi: https://chat.vlm.run/c/5bfda3c2-a2bf-4ca2-a874-78f1ce66edf1

Taylor swift: https://chat.vlm.run/c/d411c16a-e2b1-490c-85cc-9f86f2564a59

Obama: https://chat.vlm.run/c/c55fe1d6-853b-4113-bdaf-d828bee0da53

Trump: https://chat.vlm.run/c/84b57509-ed38-454a-9b17-85c03a247993

Kohli: https://chat.vlm.run/c/da8ffe8a-0818-4820-bdeb-b82d965ae3a4

Lamar: https://chat.vlm.run/c/ef6488c3-b0f0-4651-944e-7d0c4f98bdd1

Mrbeast: https://chat.vlm.run/c/c24d1cac-feb0-4a53-b1a2-2bbb62a7b7fb

New comment by visioninmyblood in "Gemini 3 Pro: the frontier of vision AI"

visioninmyblood — Sat, 06 Dec 2025 23:01:34 +0000

I tried this by using an gemini visual agent build with orion from vlm.run. it was able to produce two different images with five leg dog. you need to make it play with itself to improve and correct.

https://chat.vlm.run/c/62394973-a869-4a54-a7f5-5f3bb717df5f

Here is the though process summary(you can see the full thinking the link above):

"I have attempted to generate a dog with 5 legs multiple times, verifying each result. Current image generation models have a strong bias towards standard anatomy (4 legs for dogs), making it difficult to consistently produce a specific number of extra limbs despite explicit prompts."

Gemini 3 Deep Think is here

visioninmyblood — Thu, 04 Dec 2025 20:07:40 +0000

Article URL: https://gemini.google.com

Comments URL: https://news.ycombinator.com/item?id=46152280

Points: 3

# Comments: 0

Gaussian Splat Reconstruction from Anything via OpenAI Chat Completions

visioninmyblood — Thu, 04 Dec 2025 19:27:50 +0000

Article URL: https://colab.research.google.com/drive/17ZAyzkJNUHm_xVZX9aowCs7rXUSfsQxU?usp=sharing#scrollTo=28706645

Comments URL: https://news.ycombinator.com/item?id=46151703

Points: 2

# Comments: 0

New comment by visioninmyblood in "Qwen3-VL can scan two-hour videos and pinpoint nearly every detail"

visioninmyblood — Wed, 03 Dec 2025 04:24:44 +0000

you want get the exact coordinated by running a key point network to pinpoint which coordinates does the next click point is you can. here I show a example simple prompt which returns the keypoint location of the next botton to click and visually localize the point with a keypoint in the image

https://chat.vlm.run/c/e12f0153-7121-4599-9eb9-cd8c60bbbd69

New comment by visioninmyblood in "Qwen3-VL can scan two-hour videos and pinpoint nearly every detail"

visioninmyblood — Wed, 03 Dec 2025 00:43:44 +0000

I agree claude and chatgpt and even gemini does a poor job in detecting and cropping into a region. Some of the simplest tasks, Qwen also is great at summerization but not into solving simple vision tasks like cropping, segmentetation and detection. Here is an examples where we compared claude, gemini, chatgpt and other frontier models for simple(and complicated) visual tasks https://chat.vlm.run/showdown#:~:text=Crop%20into%20the%20cl...

New comment by visioninmyblood in "Qwen3-VL can scan two-hour videos and pinpoint nearly every detail"

visioninmyblood — Tue, 02 Dec 2025 22:13:57 +0000

I was using this for video understanding with inference form vlm.run infra. It definitely has outperformed Gemini which generally is much better than openai or Claude on videos. The detailed extraction is pretty good. With agents you can also crop into a segment and do more operations on it. have to see how the multi modal space progresses:

link to results: https://chat.vlm.run/c/82a33ebb-65f9-40f3-9691-bc674ef28b52

Quick demo: https://www.youtube.com/watch?v=78ErDBuqBEo

New comment by visioninmyblood in "Ghibli3D: Transform People into 3D Ghibli Characters"

visioninmyblood — Wed, 26 Nov 2025 20:42:57 +0000

The 3d viewer is slow, and might take time to load, thank you for your patience.

Modi: https://chat.vlm.run/c/bdbaf1dc-b3c2-4b8a-ad17-6e26d87475fd

Musk: https://chat.vlm.run/c/894f44ce-c366-4c93-b348-de6eebfb9f03

Ronaldo: https://chat.vlm.run/c/db5eff27-8c52-4e0b-8e4e-157df6bef278

Gomez: https://chat.vlm.run/c/02b92f23-a6fd-4380-b7a9-52ae7463c9c1

Jackie chan: https://chat.vlm.run/c/62ca5502-2066-4d5f-b994-c8845b2e72c9

Messi: https://chat.vlm.run/c/5bfda3c2-a2bf-4ca2-a874-78f1ce66edf1

Taylor swift: https://chat.vlm.run/c/d411c16a-e2b1-490c-85cc-9f86f2564a59

Obama: https://chat.vlm.run/c/c55fe1d6-853b-4113-bdaf-d828bee0da53

Trump: https://chat.vlm.run/c/84b57509-ed38-454a-9b17-85c03a247993

Kohli: https://chat.vlm.run/c/da8ffe8a-0818-4820-bdeb-b82d965ae3a4

Lamar: https://chat.vlm.run/c/ef6488c3-b0f0-4651-944e-7d0c4f98bdd1

Mrbeast: https://chat.vlm.run/c/c24d1cac-feb0-4a53-b1a2-2bbb62a7b7fb