Hacker Newsnew | past | comments | ask | show | jobs | submit | taikon's commentslogin


I love frigate... just had my neighbors come by because their dog was sick and were wondering if the dog had got into something in our back yard. Pulled up frigate, searched for "black dog" on the backyard camera, and found all the video of their dog.

dogs eat "post-processed food".

I wonder if there's a market for an AI dog collar that says "FIDO! don't eat that!"


Also discussed here on HN greatly:

https://news.ycombinator.com/item?id=44794508


I still remember when the website said Chroma Cloud was coming end of 2023. What took so long?

very fair!

cloud has been in private beta for a year now.

we chose to not release it to the public until we were extremely confident in the system and its characteristics.

databases are a serious business. developers trust us with their mission critical data.


Thank you!


Working on the TAIKO-01, a mass produced split curved keyboard. Planning for release in 6 months.

Join the waitlist here: taiko.taikohub.com


How's it different from e2b computer use?


We’re still figuring things out in public, but a few key differences:

- Open-source from the start. Cua’s built under an MIT license with the goal of making Computer-Use agents easy and accessible to build. Cua's Lume CLI was our first step - we needed fast, reproducible VMs with near-native performance to even make this possible.

- Native macOS support. As far as we know, we’re the only ones offering macOS VMs out of the box, built specifically for Computer-Use workflows. And you can control them with a PyAutoGUI-compatible SDK (cua-computer) - so things like click, type, scroll just work, without needing to deal with any inter-process communication.

- Not just the computer/sandbox, but the agent too. We’re also shipping an Agent SDK (cua-agent) that helps you build and run these workflows without having to stitch everything together yourself. It works out of the box with OpenAI and Anthropic models, UI-Tars, and basically any VLM if you’re using the OmniParser agent loop.

- Not limited to Linux. The hosted version we’re working on won’t be Linux-only - we’re going to support macOS and Windows too.


Active development of CUA, according to GitHub


What if it fails to mention a critically important piece of info? Would your company be liable or would I as a physician have be liable for its mistake?


Great question. Our software is designed to assist, not replace, the physician’s role in making clinical decisions. It accelerates the time between an inbound referral and patient care by extracting and organizing information, but the final review always remains with the physician.

To minimize risk, we implement safeguards to prevent hallucinations, and our system is built to flag potential missing or unclear information rather than override clinical judgment.


So I'd still need to do a full chart review? I'm not sure it would save me any significant amount of time.


How does vectorchord compare to pgvectorscale?


Thanks for the question. We will write a comparison post for it.


Hey HN, My name is David and I'm a family doctor. I made an app where you can message doctors with health related questions.

I made this after having to wait for a doctor myself for over an hour for a simple question. Plumfin lets you send your question to a licensed doctor and get a notification when they reply. This saves you an hour of waiting every time you want to ask a doctor a question.

I haven't gotten Plumfin HIPAA/PIPDEA certified yet, so for now it's only for general health information rather than personalized medical advice. Meaning you shouldn't include personally identifying information.

How it works: It uses a llama 3.2 model fine tuned on medical Q&A with RAG on a medical database. It displays this information on an internal doctor-facing dashboard, where doctors (ie. me) can select between 4 LLM written responses and edit them before sending them back. It also sends a notification to their phone to alert them of a new message. When a doctor sends a reply, you get alerted through your email of the new message.

Let me know what you think. I'd appreciate any thoughts or feedback you might have.



Anywhere you'd recommend a hobbyist can learn more about remeshing or feature detection?


This is a technical paper, but it has a quite conversational abstract and introduction that is easy enough to follow if you have some experience with mesh modelling: https://www.graphics.rwth-aachen.de/media/papers/337/learnin...



Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: