Hers is one: https://github.com/mohsen1/fesh

beats the best compression out there by 6% on average. Yet nobody will care because it was not hand written

That's a very interesting case. If you want I will look into this in more detail, I'm waiting for some parts so I have some time to kill.

Are you an expert in this field? I'm curious if the AI generated code here is actually good.

I've done some work on compression really long ago but I am very far from an expert in the field, in fact I'm not an expert in any field ;) The best I ever did was a way to compress video better than what was available at the time but wavelets overtook that and I have not kept current.

I'm curious about two things:

- is it really that much better (if so, that would by itself be a publishable result) where better is

  - not worse for other cases

  - always better for the cases documented

I think that's a fair challenge.

- is it correct?

And as a sidetrack to the latter: can it be understood to the point that you can prove it is correct? Unfortunately I don't have experience with your toolchain but that's a nice learning opportunity.

Question: are you familiar with

https://www.esa.int/Enabling_Support/Space_Engineering_Techn...

https://en.wikipedia.org/wiki/Calgary_corpus

https://corpus.canterbury.ac.nz/

As a black box it works. It produces smaller binaries. when extracted matching bit-by-bit to the original file.

I tested across 100 packages. better efficiency across the board.

But I don't know if I (or anyone) want to maintain software like this. Where it's a complete black box.

it was a fun experiment though. proves that with a robust testing harness you can do interesting things with pure AI coding

Neighbor?!

Next door? No. In the neighborhood? Undoubetly.

in Iran there's a funny situation where you're connected but not to the internet. if that makes sense.

Are you still able to access Iranian servers, or is all traffic blocked? I'd class "The servers in Iran" as still a part of the internet

It does thanks. Hope all is well if you're over there.

This is a life saver in Iran right now. Maybe only 0.01% have access to internet using Starlink

Ceno still requires an internet connection

It's possible that they use the camera to measure room brightness

I thought this too. If they're using the camera to do brightness, it needs to be on when the user isn't using it - if the activity LED is tied to the camera power rail (not sure if it is), it might look like there's something nefarious going on. No way Apple would let that go out the door.

They missed some other type of windows like Activity Monitor graphs. Those are even sharper corners!

Just wanted to see my Claude account usages

https://github.com/mohsen1/claude-usage

Interesting time to be alive. there are software similar to this but not _exactly_ what I wanted so I made it in a few hours!

Because it's a diffusion model that hardly able to redo what it just did.

Yes, but as a producer I would like to have more simplistic generations such as "Generate me 15 variations of a kick that sounds like X", I think stuff like this would be much more useful.

I really want someone to build this:

Using a webcam, monitor finger movements and find mistakes (using some sort of AI video analysis) to help user figure out how to improve. It's a hard thing to build but if you build it there is going to be paying customers. You can even sell hardware and subscriptions with it. Lots of schools want this!