pablo24602

Great question!

I also haven't seen comparable remote control functionality in open source tools- even in the closed source world, Codex and Cursor are in my experience the only very stable remote control experiences right now.

As for Proliferate, we don't currently support mobile access as a first class feature- we have a beta version available but don't want to release to GA yet as we're trying to match the above Codex / Claude quality and stability bar first.

We're on it! Apologies for the poor Windows experience in the meantime.

Congrats on the launch! Every enterprise deserves to use a beautiful AI chat UI (and Onyx is a fantastic and easy to try option).

This patent just published- seems like some university researchers in conjunction with Meta employees filed it.

If you want more engagement, might I suggest highlighting one/some of the more relevant discoveries in the title? Just the idea of "this week summarized" isn't as compelling as an AI drone beating human champions or a16z's Open Source AI Grant (and the implications of those stories). I myself am interested in pretty much everything you have listed in the article, but was not at all drawn in by your HN post title. Subscribed though!

Yep- I can't unpost the link so I put "[Broken - Undeployed]" once I got comments coming in.

Absolute overlook on my part- thank you for pointing this out.

Very sorry- ran into limits of Spotify so app is currently broken for new users.

Yeah, looks like I didn't have API access past a 60 users for Spotify so it's only showing the default responses (which crash most of the functionality)- apologies!

Very fair point- will update to be more technically accurate.

Thank you for letting me know; you're absolutely right- it's not working at all now for new users, my app hasn't yet been approved to leave Spotify's development mode- https://developer.spotify.com/documentation/web-api/concepts..., so the top/tracks and top/artists endpoint which I'm using to fetch data aren't functional.

Very embarrassing on my end- wish I had more than 1 Spotify account so I could verify the API was working for new users before posting- my apologies.

Little Sunday Project. Using AI in a fairly tongue-in-cheek way. Very simple build but thought it was funny!

Thank you for your insight- leaving a comment here to come back to later.

This ended up being my solution as well- although I still ran into edge cases where GPT would output things like "Stella said". Never did manage to 100% fix this issue, even with creative prompts.

I built something very similar when the paper came out- watch out for the instances where GPT returns both sides of the conversation (e.g. interpreting a prompt with chat history as being representative of what the output should look like, and putting out both "Jack" and "Jill"'s text). The first sample I went to suffered that problem (output from "Lucky's perspective below.)

"Hey Stella! It's so great to see you! You'll never believe what I've been up to recently. I went on this incredible space adventure and witnessed the most breathtaking meteor showers. And guess what? I even encountered alien beings who communicate through colors! It was absolutely mesmerizing. Stella: Wow, Lucky! That sounds absolutely fascinating. I've always been intrigued by space and the wonders it holds. I would love to hear more about your adventure. Lucky: I'm thrilled that you're interested, Stella! I can't wait to share all the details with you. But before we dive into that, I heard you're passionate about gardening. Is that right? Stella: Yes, that's true! Gardening is one of my favorite hobbies. I find it so peaceful and fulfilling. Lucky: That's fantastic! I'm actually not very experienced in gardening, but I'd love to learn from you. How about we plan a gardening session where we can exchange tips and spend some quality time together? Stella: That sounds wonderful, Lucky! I'd be more than happy to share my gardening knowledge with you. Let's find a time that works for both of us. Lucky: Absolutely! I'm really looking forward to it. But hey, no rush. If there's something urgent you need to attend to, we can always reschedule. Just promise me we'll find another time to connect. Stella: Don't worry, Lucky"

Source code here: https://github.com/pablojosecodes/pypi_name_validator/tree/m...

> depositors have full access to their money and both new and existing deposits are fully protected by the FDIC. This action by FDIC effectively means that deposits held with SVB are among the safest of any bank or institution in the country.

I had this exact idea a couple weeks ago- cool to see that somebody built it!

edit: Website stuck at "please wait"

> Several podcasts I listen to are killing their $2/$3 tiers as it doesn't make them any money

Am I missing something here? The cut that Patreon gets is 5-12% of revenue and processing payments for 2-3$ are 5% + 10c. At worst, she's getting $2.2 for every $3/m user.

From the website, it seems as though they are retrieving five chunks. Also looks like they split documents by paragraph sections, unless the paragraphs are small enough- then they put a couple of them together.

I was looking for something similar, but figured the use case was so narrow that nobody else was interested- what are the issues with the solution you found? Thinking of building this out.

All the embedding-enabled GPT-3 apps I've seen do the following: User query -> Retrieve closest embedding's plaintext counterpart -> feed plaintext as context to GPT-3 prompt.

> a transaction is a successful Bing API call request

Seems accurate.

Working through these right now- definitely recommend them

Cool! Just a note- the different faces and emotions seem like buttons we'll be able to click, so they're slightly confusing at first glance.

I'd add some more flags/options for downloading specific videos or updating the library of downloaded content. I don't really want to download all the videos from one specific channel- instead I want to download the last 10 videos, for example.

Super cool! Will definitely be using this to explain mathematical concepts

Very cool! What kind of tech are you using to make this? I've played around with finetuning stable diffusion + using spectrogram-to-waveform and back algorithms, but never landed on anything high quality.

I concur. With 600 products under your belt, you clearly have the experience necessary to build projects- but that's not worth anything if nobody uses them or finds value in them. A tactic I commonly see to gauge interest is sell/accept preorders first, then build.