Jan Hosang

I'm located in Switzerland, I got no ads at all. And just now rechecked, no ads at the start.

Only realized now that I never got any ads on your videos that's insane! Noclip choosing aesthetics over money any day

@jesseguarascia.com Hey Jesse, a while ago on the crewcast you mentioned a puzzle game to defrag your brain when life is tough. Do you remember which one it was?

I know Google doesn't have the reputation, but I think the commitment of blurring SV and aerial data on request predates GDPR by years.

And unfortunately those requirements bleed into the model weights, too.

Oh boy do I wish that was the reason. SV data is super sensitive and we have to comply with takedown requests.

YouTube video by i am a dot. The Game That's IMPOSSIBLE to Master

youtu.be/8w8s5P4OYko?...

I believe it can also mean that it explains the difference between Y% of the pairs of individuals (instead of Y% of the difference for each pair). More generally, I think it can also mean it explains A% of the difference for B% of the pairs, s.th. A*B=Y.

It's still magic even if you know how it's done.
- Terry Pratchet

The hidden layer is intriguing, but I cannot imagine really enjoying the normal room building mechanics, so I thought I'd ask before taking the plunge. Thanks for answering!

@jeremybjayne.bsky.social did "that moment" end up happening in blue prince that you were wanting for?

Wow! Do you know why? What a marketing scam.

I agree. That the highest profile institution gives half pay for >100% work is not ok. And not taking allegations seriously is unacceptable, particularly as a publicly funded institution.

How did you know what to change to encourage emergence?

That probably depends on the task, right? Have you done a specific experiment? For needle-in-haystack I can imagine that. For correspondence tasks not really.

If you believe you can cram all information into one vector, then maybe it's not such a stretch to believe you can go over the points in random order? Though I have a hard time buying that.

I mean bsky feed of course.

Maybe we should make a bsky list for paper discussions? My feed is a little messy.

The surprise of a paper's results should be given more weight also while reviewing. We overindex so hard on novelty or flat numbers, instead of insights.

If we use permutation invariant models for sequence modeling, what would be more fitting than using sequence models on unordered sets? /s

I've been fascinated by the sound Hammond organs (not sure if that's the right term) make when playing more tones at the same time. Maybe the overtones interact in interesting ways? But I love this growl, too. It's great when key instruments get the expressive range of electric guitars for example!

How does the low E get so dirty? Is it just a timing based effect?

I love it!

!remindme 14 days

"share the same last braincell". I'm stealing this one.

Nice to dog-meet! Morning walks need to be foggy.

Thanks, Chris! That's one I'm definitely aware of. I'd be more interested in semantic features than coming up with the points only.

Anybody working on 3D foundation model pertaining from (posed) multiview images? Any pointers to ideas or papers to read?

Maybe it would make sense to specify which part of AI/ML the feed is about. MLsky is so focused on neurology (effectively, I suppose not by design) that I end up not reading it. I am interested, but it's just too skewed.

Thanks for setting up a feed. Please add me, too! :)

@venteto.bsky.social Example: github.com/hosang/bsky-...