HackerTrans
TopNewTrendsCommentsPastAskShowJobs

hmdai

no profile record

Submissions

Living Canvas: A web-based puzzle game powered by Generative AI

github.com
1 points·by hmdai·l’année dernière·0 comments

Why MCP can't be as simple as Naive Context Protocol

github.com
4 points·by hmdai·l’année dernière·1 comments

Show HN: I made a MIDI-based Piano training app

piano.hiku.app
2 points·by hmdai·l’année dernière·0 comments

Tell HN: ChatGPT adds utm_source=chatgpt.com to external links

4 points·by hmdai·il y a 2 ans·1 comments

Ask HN: Is Git commit history useful to you?

2 points·by hmdai·il y a 2 ans·10 comments

Ask HN: Please share your experience with CouchDB vs. other doc-oriented DBs?

2 points·by hmdai·il y a 2 ans·1 comments

Ask HN: What do you recommend for implementing access control?

2 points·by hmdai·il y a 2 ans·3 comments

Ask HN: Which User Management (Identity, Access) tool do you recommend?

1 points·by hmdai·il y a 2 ans·0 comments

Ask HN: Is anyone using alternative open email protocols like JMAP?

15 points·by hmdai·il y a 2 ans·3 comments

I hate what the internet has become

hmd.ai
6 points·by hmdai·il y a 2 ans·0 comments

Ask HN: What is good about tailwindcss if you mostly use a component lib?

1 points·by hmdai·il y a 2 ans·0 comments

[untitled]

1 points·by hmdai·il y a 2 ans·0 comments

Deno 1.42: Better dependency management with JSR

deno.com
3 points·by hmdai·il y a 2 ans·0 comments

The Road to Fresh 2.0

github.com
2 points·by hmdai·il y a 2 ans·0 comments

Show HN: I made a (Y) scraper to see the progress of batch W24 websites

curved-locust-c486.hiku.app
1 points·by hmdai·il y a 2 ans·0 comments

Offline GPT Store – Run LLMs Locally Using WebGPU

offlinegpt.store
3 points·by hmdai·il y a 2 ans·0 comments

What services YC batch W24 use on their websites

curved-locust-c486.hiku.app
1 points·by hmdai·il y a 2 ans·1 comments

Economic Inequality (January 2016)

paulgraham.com
1 points·by hmdai·il y a 2 ans·0 comments

Ask HN: What are the downsides of hosting your blog on a separate subdomain?

3 points·by hmdai·il y a 2 ans·2 comments

Google's Chromium team working on non-WebKit browser for iOS (Feb 2023)

appleinsider.com
2 points·by hmdai·il y a 2 ans·0 comments

comments

hmdai
·il y a 4 mois·discuss
Genuine question, why can't this be done via an API that the agents call? there are already established ways to call APIs on behalf of the user. Seems to me that the agent is loading a web app just to be able to access it's apis, what am i missng?
hmdai
·l’année dernière·discuss
I absolutely love this, bonus: I can now read Cuneiform numbers, if I ever need that.

Suggestion: You can potentially show the Cuneiform time in the url.

sent at: 𒌋:𒎙𒐛:𒐏𒐗
hmdai
·l’année dernière·discuss
[flagged]
hmdai
·l’année dernière·discuss
Since the introduction of Model Context Protocol, I've been wondering why this protocol is so complicated to work with and after many wasted hours and a few MCP spec updates, I've decided to write down what I think MCP should have been and I call it Naive Context Protocol ¯\_(ツ)_/¯.

Maybe this approach is in fact naive (please tell why!), the "spec" is very minimal at this point (I will expand based on feedback here) and it probably ignores some use-case (some of them on purpose), but I would like to hear:

1. What everyone here thinks the MCP/NCP should've been/should be?

2. What use-cases would you like a context protocol to support?
hmdai
·l’année dernière·discuss
I'm building a client-side encrypted personal management tool for myself, with support for file encryption:
hmdai
·il y a 2 ans·discuss
Does anyone know if the search will be available through their api? seems like a unique offering that not even google has (to my knowledge at least)
hmdai
·il y a 2 ans·discuss
Inspired by Paul Graham tweet:

"You could probably make a lot of money simply by investing in companies that a significant percentage of the latest YC batch use. They're the quintessential early adopters."

I wanted to see what services are used on batch W24 company websites. Of course this not a complete representation since it doesn't include internal, server side or behind authentication services.

These numbers are out of 197 total companies in batch W24:

- Octolane is the most popular company in W24 so far, used by 10 within the batch.

- 88 use Google analytics vs 2 that use Plausible

- Many use webflow (50) or framer (42) to build the website

- Youtube (19), loom (5) and Mux (4) for video
hmdai
·il y a 2 ans·discuss
Do you have a link to the source of this info?
hmdai
·il y a 2 ans·discuss
Try this one: https://uneven-macaw-bef2.hiku.app/app/

It loads the LLM in the browser, using webgpu, so it works offline after the first load, it's also PWA you can install. It should work on chrome > 113 on desktop and chrome > 121 on mobile.
hmdai
·il y a 2 ans·discuss
Can you at least provide guidance on how to avoid wrongly getting flagged like this?
hmdai
·il y a 2 ans·discuss
Read more about why webgpu is required here: https://webllm.mlc.ai/ (that's the project that is used here)
hmdai
·il y a 2 ans·discuss
You can make any chat you want by saving the last message, e.g. if you just need a friendly chat bot, you can create that as well.
hmdai
·il y a 2 ans·discuss
The underlying model is created for webgpu, not to mention the feasibility of running LLM with webgpu, read more here: https://webllm.mlc.ai/
hmdai
·il y a 2 ans·discuss
Thanks! It's using Llama 2 7B, It supports bigger models but those take longer to download and also infer (if run at all depending on the device)
hmdai
·il y a 2 ans·discuss
I think I can't trust a therapist enough to be completely honest, while I can just write anything into the chat, knowing no one, (except google) will ever know :D
hmdai
·il y a 2 ans·discuss
I wanted a privacy preserving AI chat bot since I didn't feel comfortable about putting personal issues into ChatGPT. It uses webllm models to run in the browser. Make your own chat by saving a message.

Disclaimer: I'm the creator of https://hony.ai that was used to build this demo.