umaar

Was able to build a personal MCP server that connects to the Jules API, letting me dispatch tasks to Jules, from Copilot Chat in VS Code.

Video here: https://www.youtube.com/watch?v=RIjz9w77h1Q

Drawing an SVG of a pelican on a bicycle. Claude 3.7 edition: https://x.com/umaar/status/1894114767079403747

I imagine it's not, but can also see automated systems flagging the number as being the recipient of messages for over a hundred different financial institutions.

Was the number used to sign up for, and receive communications from credit card companies? Is the ban related to signing up for +100 cards?

https://www.dannyguo.com/blog/my-credit-and-debit-card-colle...

I made a video showcasing some advanced techniques to use fonts on the web, without compromising performance. Covers interesting font metrics like ascenders and descenders. Fascinating to see how much information is contained within a font file!

https://www.youtube.com/watch?v=wSOIbdOaKR8

Really like the simplicity of your website. I think when you first announced it, you mentioned you might open source Magic Loops, might you do that?

This is a tutorial I wrote for Firebase. It shows how to build three different AI-related web apps: A chatbot, a review summariser, and a video summariser.

https://umaar.com/blog/

There's also hundreds of developer tips here https://umaar.com/dev-tips/

You can do this with Workspaces and it works well. Made a video on this here: https://moderndevtools.com/lessons/12

Using DevTools, you can extract all styles, even if they're scattered across loads of tailwind utility classes. Made a video on how to do this here: https://umaar.com/dev-tips/261-devtools-copy-all-styles-for-...

If anyone wants to self-host these YouTube summary tools, made a video on exactly how to do that here https://youtu.be/dqtliRSLmQo

Hey HN, have seen a lot of AI demos recently using libraries/frameworks for what is effectively an API call - so thought to showcase how this could be done with vanilla JavaScript. Turns out response.body is an async iterable, so you can do something like:

  for await (const chunk of response.body) { // use chunk }

This blog post shows S3 Glacier Deep Archive costs $2.05 USD for 2 TB but on the AWS pricing page it's showing as 2,000 GB * $0.0018 per GB = $3.60 ?

Edit: this is for London pricing, guess it's a bit higher.

This is a great project and it was fun playing around with it.

When Meta started discussing this in 2021, the HN sentiment [1] was quite...cautious, making connections to how Meta can't be trusted with kids drawings. Has something changed?

[1] https://news.ycombinator.com/item?id=29580619

I have stuck with cheap VPS servers for as long as I can remember. It takes 5 minutes to deploy a full stack node.js app, along with a database - and I've yet to exhaust the resources on my VPS, even with all my side projects (production grade and hobby stuff).

Have always found it weird how so many heroku-style hosting providers charge _per app_, things get costly, quickly, when you have lots of small apps like I do.

Just yesterday I realised I'll need a database to store job queues for https://chatbling.net - ChatGPT helped me figure out how to install it, have it persist to disk, ensure it starts up with the system etc. It's nice to not be fearful of unexpected charges hitting my card.

To anyone reading, even if it's just for learning, every now and then, skip the vercel/fly.io/netlify/planetscale/upstash/render/railway whatever cool hosting provider is out, and give a $5 VPS a try.

Agreed, giving the user a choice would be best here. Something tells me most users would not change it from whatever the default is, but yeah still good to expose this as a setting which should be doable. Thanks for the input!

I see my server has restarted a few times! I imagine it's folks here since I haven't shared Chat Bling elsewhere yet. Sorry to anyone who started generating images, but haven't received a response. The 'jobs' for images generations are stored entirely within memory, so a server restart will lose all of that.

Going forward, I'll explore storing image jobs in redis or something, which will be more resilient to server crashes.

As for conversation history, I'll continue to keep that in memory for now (messages are evicted after a short time period, or if messages consume too many OpenAI tokens) - even that's lost during a server restart/crash. Feels like quite a big decision to store sensitive chat history in a persistent database, from a privacy standpoint.

Hey HN, I made Chat Bling. An AI chat bot that works with official WhatsApp APIs. You can:

- Chat with ChatGPT directly from WhatsApp.

- Generate pretty cool images (see the home page for screenshots).

- Transcribe your WhatsApp voice messages - speech to text using Whisper.

No signup needed, thank you, let me know if you have any questions or feedback.

Made something similar recently, but for WhatsApp: https://chatbling.net/

What behaviour would users prefer when uploading a voice message, a) the voice message is transcribed, so speech to text? Or b) the voice message is treated as a query, so you receive a text answer to your voice query?

I've done a) for now as mobile devices already let you type with your voice.

Incredible results to my questions. Do these work by finding similar pieces of text from a vector DB, and then embedding those similar pieces of text in the prompt? The answers I'm getting seem to be comprehensive, as if it has considered large amounts of book text, curious how this works as there's an OpenAI token limit. I've heard this is what tools like langchain can help with, so maybe I should play around with that as this all seems like a mystery to me.

Thank you!

I remember using Splunk (where the author used to work) at a previous job.

In the spirit of sharing What I learned at X, here's What I learned at Shazam:

Part 1: https://umaar.com/blog/lessons-learned-from-working-at-shaza...

Part 2: https://umaar.com/blog/lessons-learned-from-working-at-shaza...

Excited to see what comes of it. Lots of people will have a private corpus, and the idea that we can semantically query it sounds so interesting.

Like asking 'what streaming services am I paying for and how much have I spent on them to date?', and some tool going over your bank statements to pick out spotify, netflix etc. I could see being useful.

https://simonwillison.net/2023/Jan/13/semantic-search-answer...

Wouldn't this approach be quite brittle? For example, where would one define snippet boundaries - isn't it possible that extracting a snippet at arbitrary points may change the information within that snippet?

But then you have the issue of GPT3 token limits, so you're limited in how many of these relevant snippets you can embed into a prompt. Wondering if there's a better way to go about this (for your first example, rather than OPs use case).

Umar Hansa: https://www.youtube.com/@UmarHansa

Made a few videos to help front-end web developers. Such as how to use DevTools, a bit about web performance and other related things.

I used to work at Shazam as a front-end web developer and they really supported me. Going to conferences, hackdays (20% time), being exposed to real production-grade systems, it was great. Very grateful to have worked there.

Wrote about it too: https://umaar.com/blog/lessons-learned-from-working-at-shaza...

I've created a collection of 200+ tips like this on my website: https://umaar.com/dev-tips/

Interesting, I think that's because logged objects are "live", so you can inspect their current state, not just the state at the point of logging.

Another! If you inspect a console.logged function, DevTools shows you the scope it has access to.

https://umaar.com/dev-tips/117-inspect-function-scope/

I've put over 200 tips like that on my website: https://umaar.com/dev-tips/

Each tip has a textual explanation, and an animated gif if you're a visual learner (I know, I need to scrap gifs and move to regular videos).

There's a lot of tricks there which can hopefully improve your development and debugging workflows. Let me know if there are specific things you'd like to see. A few people have asked for how to find memory leaks.