Hacker Newsnew | past | comments | ask | show | jobs | submit | more nullandvoid's commentslogin

Just a heads up I had to go on VPN with a US IP for this to load, strangely a resential UK one didn't


https://www.youtube.com/watch?v=QYVucud3ptc has good coverage of running locally and via web (https://fal.ai/models)


Sure, but I think you're missing the point.

The point is that many athletes are only at their peak for one or two Olympics. How rubbish for them that they're not able to get a fair shot at the record like others have had in the past.


Anyone have any home project ideas (or past work) to apply this to / inspire others?

I was initially thinking the obvious case would be some sort of system for monitoring your plant health. It could check for shrinkage / growth, colour change etc and build some sort of monitoring tool / automated watering system off that.


I used the original SAM (alongside Grounding DINO) to create an ever growing database of all the individual objects I see as I go about my daily life. It automatically parses all the photos I take on my Meta Raybans and my phone along with all my laptop screenshots. I made it for an artwork that's exhibiting in Australia, and it will likely form the basis of many artworks to come.

I haven't put it up on my website yet (and proper documentation is still coming) so unfortunately the best I can do is show you an Instagram link:

https://www.instagram.com/p/C98t1hlzDLx/?igsh=MWxuOHlsY2lvdT...

Not exactly functional, but fun . Artwork aside it's quite interesting to see your life broken into all its little bits. Provides a new perspective (apparently, there are a lot more teacups in my life than I notice).


Wow, that’s really cool!


After playing with the SAM2 demo for far too long, my immediate thought was: this would be brilliant for things like (accessible, responsive) interactive videos. I've coded up such a thing before[1] but that uses hardcoded data to track the position of the geese, and a filter to identify the swans. When I loaded that raw video into the SAM2 demo it had very little problem tracking the various birds - which would make building the interactivity on top of it very easy, I think.

Sadly my knowledge of how to make use of these models is limited to what I learned playing with some (very ancient) MediaPipe and Tensorflow models. Those models provided some WASM code to run the model in the browser and I was able to find the data from that to pipe it though to my canvas effects[2]. I'd love to get something similar working with SAM2!

[1] - https://scrawl-v8.rikweb.org.uk/demo/canvas-027.html

[2] - https://scrawl-v8.rikweb.org.uk/demo/mediapipe-003.html


Plasmo has a messaging library you might want to explore

https://docs.plasmo.com/framework/messaging


For me it's not intimidating, it's just time consuming. I can create / iterate twice as fast when I'm styling inline with my HTML. It could be with tailwind, or other utility based libraries - tailwind has just done it the best from my experience.


I think it's the unnecessary insertion of emoji's next to words, and flashing of the current word that OP is talking to.

No one is is arguing subtitles are bad, it's the way this tries to increase engagement through abusing attention mechanisms, that I also agree with OP is likely damaging to us.

It's part of the many reasons I dislike the current short form media craze - horrible tactics like this are used more often than not.


Exactly. And since the human mind has limited attention capacity, I feel it desensitizes people from paying attention to "normal life". People look like zombies.


How much is it costing you? Charge a markup on that you're happy with rather than picking a number out of thin air?

Also set a healthy free limit, if people are already paying for one product, they're not going to want to pay for an API separately if they just want to make a few calls.


+1 discover weekly consistently delivers a few new songs to my like list - I actually look forward to it each Monday when I start work.


My main complaint with Spotify's recommendations algorithm is that you cannot provide any clear negative feedback to it anymore.

I played a single Christmas album from an artist that my mom wanted to hear over the holidays, but I don't like that artist or style of music otherwise.

Now, every time they release a new song it comes up in my release radar, and random similar things pollute my discover weekly.

There's no way to say "never recommend this to me" or to remove past listens from my history. I'm just forever doomed, apparently, to get jumpscared with Christian contemporary music anytime I try to play these playlists.


Yeah fair enough, I have had the occasional few months where it goes a little haywire (too skewed to a genre / style I was just curiously listening to, rather than wanting more of).

It does seem to fix itself - although a negative feedback mechanism would be nice!


I was hoping to use it to generate some sound effects to use in a game I'm working on - but looks like I need an "enterprise license" (https://www.stableaudio.com/pricing)

Why does this have a different clause I wonder, and doesn't just fall under "In commercial products below 100,000 MAU"?


Different deal with the underlying data holders with revenue share etc


Consider applying for YC's Winter 2026 batch! Applications are open till Nov 10

Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: