fzysingularity

3 ngày trướcdiscuss

The ICP question was more around the model itself. Are they looking to license it to robotics companies? Do they imagine that devs at robotics companies would be willing to deploy these models as a black box?

fzysingularity

3 ngày trướcdiscuss

It’s unclear to me what their desired outcome for a blog post like this. If you’ve ever worked in a robotics setting, 80% implies that 20% of your autonomous actions are incorrect. Imagine if this were the case for autonomous driving where your car misbehaves 1 in every 5 actions it takes.

Posts like this just reminds me of the end to end demos AV companies built in the early days using a single camera - only to realize that it’s harder than it looks years later into development.

fzysingularity

3 ngày trướcdiscuss

Frontier labs are realizing that software/models themselves don’t have real moats and move to embodied ai.

SOTA 80% means a practically useless robot. What are they really imagining their ICP to be here?

fzysingularity

5 ngày trướcdiscuss

It's live now, https://github.com/vlm-run/mm.

fzysingularity

5 ngày trướcdiscuss

We were planning to open-source this soon, but jumped the gun and posted about the video encoders here since it seemed relevant.

In either case, here you go, it's public now: https://github.com/vlm-run/mm.

fzysingularity

9 ngày trướcdiscuss

Exactly! We experimented with a whole bunch of video encoding techniques for LLMs here: https://vlm-run.github.io/mm/encoders/#video

fzysingularity

9 ngày trướcdiscuss

Pretty terribly expensive way to watch a video with Claude.

Use Gemini or some local VLM to do this way more efficiently. We spent quite a bit of time on video understanding, and Claude will just burn tokens.

Check out this library: https://vlm-run.github.io/mm/

You can swap models and try out different encoding methods for videos (https://vlm-run.github.io/mm/encoders/#video)

fzysingularity

18 ngày trướcdiscuss

This is neat. I'd love to figure out a sequence of emojis that triggers the LLM in ways that puzzles a human.

fzysingularity

tháng trướcdiscuss

That’s a pretty large binary for simply loading images.

In all honesty, opencv has stood the test of time and I’m certain newer LLMs will likely not attempt to rewrite it from scratch.

P.S. I’ve been a user since the IplImage days, circa 2007, and I’d still consider using it over most CV libraries today.

fzysingularity

tháng trướcdiscuss

I can’t help but think that there are so many astroturfed comments in here.

Seems like a concerted and distributed effort from the entire Anthropic team every time to get this on top of HN.

fzysingularity

tháng trướcdiscuss

Kind of crazy how many bespoke python sandbox implementations have popped up in the past few months.

I’d love to see if we can get GPU access within these runtimes, that’d be awesome.

fzysingularity

tháng trướcdiscuss

What’s your experience with Monty? Been looking at it for one of our environments and it seems very promising.

fzysingularity

2 tháng trướcdiscuss

VLM Run (https://vlm.run) | 1x Product + 1x ML Staff Engineer | Santa Clara, CA (HQ)

We're building the inference and orchestration layer for production Vision-Language Models. We care deeply about fast and ergonomic visual inference, reliable structured outputs, and the observability to iterate on them.

A few things we've shipped recently you can poke at:

  1. Orion: our visual agent that reasons and acts over images, video, and documents. Chat at https://chat.vlm.run.
  2. mm-ctx: a Unix-style multimodal CLI (find, cat, grep, wc) that gives coding agents real context over images, video, and PDFs. Rust core, Python devex. 
  3. vlmbench:  single-file CLI for benchmarking VLM inference (TTFT, TPOT, throughput) across vLLM, Ollama, and SGLang.

Apply: https://app.dover.com/jobs/vlm-run

Email hiring "at" vlm.run with your GitHub + a couple recent projects.

[1] https://chat.vlm.run

[2] https://pypi.org/project/mm-ctx | https://www.vlm.run/open-source/mm

[3] https://github.com/vlm-run/vlmbench | https://www.vlm.run/open-source/vlmbench

fzysingularity

3 tháng trướcdiscuss

The recent claude code leak also revealed that they're poisoning their competitors via anti-distillation policies baked in claude code CLI (fake tool calls, adding noise etc).

fzysingularity

3 tháng trướcdiscuss

VLM Run (https://vlm.run) | 1x Infrastructure Engineer + 2x AI/ML Engineer | Santa Clara, CA (HQ)

VLM Run is building infrastructure for production Vision-Language Model (VLM) systems — fast inference, tool-use + orchestration, reliable structured outputs, and the observability to iterate quickly. We’re a deeply technical team of veteran AI / computer-vision engineers (20+ years combined, MIT/CMU PhDs) who’ve shipped production ML infrastructure across autonomous driving and LLMs.

Open roles:

1. Infrastructure Engineer (Full-time, ONSITE): $150K–$220K + 1–3% equity https://app.dover.com/apply/VLM%20Run/8d4fa3b1-5b38-42e1-927...

2. AI/ML Engineer (Full-time, ONSITE): $150K–$220K + 0.5–3% equity https://app.dover.com/apply/VLM%20Run/1a490851-1ea1-4f12-a0f...

Email hiring "at" vlm.run with your GitHub + a couple recent projects.

P.S. We recently launched Orion, our visual agent that can reason and act over images, videos and documents. You can chat with Orion at https://chat.vlm.run and see capabilities at https://docs.vlm.run.

Apply: https://app.dover.com/jobs/vlm-run

fzysingularity

4 tháng trướcdiscuss

Real-time or continuous learning is great on paper, but to get this to work without extremely expensive regression testing and catastrophic forgetting is a real challenge.

Credit to the team for taking this on, but I’d be skeptical of announcements like this without at least 3–6 months of proven production deployments. Definitely curious how this plays out.

fzysingularity

4 tháng trướcdiscuss

What do you think actually happened here in the past week?

They used Kimi, failed to acknowledge it in the original Composer announcement. Kimi team probably reached out and asked WTF? Their only recourse was to publicly disclose their whitepaper with Kimi mentioned to win brownie points about being open about their training pipeline, while placating the Kimi team.

fzysingularity

4 tháng trướcdiscuss

VLM Run (https://vlm.run) | 1x Infrastructure Engineer + 2x AI/ML Engineer | Santa Clara, CA (HQ)

VLM Run is building infrastructure for production Vision-Language Model (VLM) systems — fast inference, tool-use + orchestration, reliable structured outputs, and the observability to iterate quickly. We’re a deeply technical team of veteran AI / computer-vision engineers (20+ years combined, MIT/CMU PhDs) who’ve shipped production ML infrastructure across autonomous driving and LLMs.

Open roles:

1. Infrastructure Engineer (Full-time, ONSITE): $150K–$220K + 0.5–3% equity https://app.dover.com/apply/VLM%20Run/8d4fa3b1-5b38-42e1-927...

2. AI/ML Engineer (Full-time, ONSITE): $150K–$220K + 0.5–3% equity https://app.dover.com/apply/VLM%20Run/1a490851-1ea1-4f12-a0f...

Email hiring "at" vlm.run with your GitHub + a couple recent projects.

P.S. We recently launched Orion, our visual agent that can reason and act over images, videos and documents. You can chat with Orion at https://chat.vlm.run and see capabilities at https://docs.vlm.run.

Apply: https://app.dover.com/jobs/vlm-run

fzysingularity

4 tháng trướcdiscuss

AI allows you to accelerate the initial build process, but I think engineering is all about craftsmanship. Today most LLMs have poor taste and chipping away the cruft matters more than ever.

fzysingularity

5 tháng trướcdiscuss

uvx probably is the way to go here (fully self-contained environment for each skill), and use stdout as the I/O bridge between skills.

fzysingularity

Submissions

Omnigent: Meta-Harness for Coding Agents (Claude Code, Codex, Cursor, Pi)

[untitled]

DeepSeek OCR 2: Visual Causal Flow

Unified Vision-Language Agents – Detect, Segment, OCR, Generate and More

VLM Showdown: GPT vs. Gemini vs. Claude vs. Orion

Show HN: Chat with Orion – a visual agent that sees, reasons and acts

ChatGPT uses YOLOv8 to detect UI elements

comments