maxkrieger

Thanks <3

I have some API credits but I intend to make it sustainable. If any LLM provider wants to sponsor some credits, hit me up.

Otherwise I’ll switch models and add user accounts.

I have a lot of OpenAI API credits to use by end of the month, so I’m using 4o. I’ll probably switch to a more sustainable model afterwards, consider this a request for API credits, all! Email’s on website :)

On a side note, I love the illustration style, some sort of colorful mixed-media collage of UI widgets and physical setting. Does anyone know any similarly-styled documents?

This artist "dustn" evokes similarly https://www.instagram.com/duztns/

> There’s no official API for ChatGPT yet, so I’m using the unofficial chatgpt NPM package to wire up the app in the demo video. OpenAI has their Cloudflare protection cranked up high; to get around that, it runs a full Chrome instance (!) in the background to shuttle messages back and forth between the little REST API server I wrote and ChatGPT’s internal API.

This is quite a workaround, have you tried the official Davinci003 api? It's rather capable now and probably faster response times. Very cool experiment regardless!

thanks, this is a great idea. Curious how it stacks up against other libraries.

Yup, check the menu in the corner or long-press anywhere in the empty space.

Coming soon! https://github.com/maxkrieger/voiceliner/issues/17

Upvote here :) https://github.com/maxkrieger/voiceliner/issues/6

I'm less bullish on specific deadlines for these kinds of notes. I'm planning to do a weekly summary notification - "you made X notes last week, Y of them were high-priority" https://github.com/maxkrieger/voiceliner/issues/20

EDIT: If you feel strongly about this and think it's possible please send in PRs. Thanks!

Unfortunately you then lose ability to play back the original audio https://stackoverflow.com/questions/2319735/voice-recognitio.... This is a major usability tradeoff IMO, though I'm willing to be swayed to add an option.

I suspect Google's limiting this because they don't want devices "freeloading" their cloud transcription service, since most phones can't do it on-device.

It follows system settings, but I'm going to add app-specific localization soon! https://github.com/maxkrieger/voiceliner/issues/17

on iOS, it's on-device. on Android, Azure - so far I haven't hit the free limit of 5hr/mo. Might start charging Android users if we hit the free limit.

It’s certainly awkward! I’m personally willing to stomach it because it’s kinda cool to “invent a new social primitive”, as dorky as it appears. There’s a very real tradeoff between mere awkwardness and fumbling with a text entry/forgetting the thing altogether.

I also recently rolled out a “create text note” escape hatch in the menu.

Hey HN! A few months ago, all I wanted was a voice memos where I could hold-to-record. Holding and releasing lets me “burst” quick chains of thoughts together. It’s especially useful when walking with friends, to capture stray references and ideas.

After testing the initial burst interaction, I realized I wanted to transcribe them, and relate notes together into a hierarchy. Other features came naturally, like geotagging each note and swiping during recording to change the “temperature” (importance) of a note.

The app is open source and written in Flutter.

There's also https://eulertour.com

Dunno if it's apples and oranges for you, but I've seen Zig [0] being thrown around here previously as a "safer" embedded C alternative, albeit more minimal than Rust. May be worth comparing (I haven't tried either language).

[0] https://ziglang.org/

This is true but only at present.

An analogy would be the weights of pretrained machine learning models. They're still serializable, though it's true they're less semantically trackable than a well-written TikZ snippet (which, by the way, I haven't seen many of in practice!)

I work on the SVG renderer for Penrose and would love to reach out and see if there's anything we can do to improve this! The renderer is written declaratively in react so it's easy to add supplemental tags or even a more readable DOM hierarchy.

There is something very whimsical about a pocket-sized lisp machine.

I wonder what the experience of (junior?) high school would have been like if students were given something like this instead of a TI-84. Math and science classes could focus on constructing playable models that answered the questions posed by the instructors a la "Structure and Interpretation of Classical Mechanics" [0]. Obviously there are some ergonomics issues but I'm still going to daydream about the concept.

If people are interested in these kinds of ideas I highly recommend "Mindstorms" by Seymour Papert [1].

[0] https://mitpress.mit.edu/sites/default/files/titles/content/...

[1] https://en.m.wikipedia.org/wiki/Mindstorms_(book)

Great concept. It seems like the graph view is begging to convey more information. At the very least it seems appropriate for the nodes to have an icon based on what kind of data they contain, for instance, a paperclip or document for an attached paper, a histogram for univariate data, a regression plot for bivariate, etc.

Replace with "Linux distribution", "compiler", or any other self-referential system https://en.m.wikipedia.org/wiki/Self-hosting

Check out using the Kindle as a raspberry pi display:

http://ponnuki.net/2012/09/kindleberry-pi/

https://maxogden.com/kindleberry-wireless.html

There are a couple dockerized jupyter and beaker kernels for WebPPL if you want a go at v2, but I had varied success with them.

...Despite the overwhelming evidence for the contrary (see pycon)?