mackopes

32" when?

Hey community!

SOGS compression keeps coming up here as a go-to method for reducing Gaussian Splatting model sizes. I put together a deep dive into how SOGS actually works under the hood, with some practical insights on how it can be used in production.

The article stays fairly high-level, but I'm happy to dive into specifics in the comments. I learned quite a bit from implementing my own version of SOGS compression.

Show me another consumer hardware that handles inference and/or training better. How many RTX5090s would you need?

For some time I have a feeling that Apple actually IS playing the hardware game in the age of AI. Even though they are not actively innovating on the AI software or shipping products with AI, their hardware (especially the unified memory) is great for running large models locally.

You can't get a consumer-grade GPU with enough VRAM to run a large model, but you can do so with macbooks.

I wonder if doubling down on that and shipping devices that let you run third party AI models locally and privately will be their path.

If only they made their unified memory faster as that seems to be the biggest bottleneck regarding LLMs and their tk/s performance.

It's weird to see only one word at the time. I don't think this reflects my true typing speed as I have a tiny pause to read the word once it shows on the screen. On the other hand, I'm able to read multiple words ahead as long as I can see them and naturally remove the pause.

Working on a platform to host and share 3D Gaussian Splatting models.

The key goal is that the creators of 3DGS models can use Blurry as a powerful tool to build the 3D experience that is performant, simple, and aesthetically pleasant for end users (viewers).

3DGS models can be shared via a link or embedded on a website, notion, etc..

Link: https://useblurry.com

I'm not convinced that there is one generalised solution to sync engines. To make them truly performant at large scale, engineers need to have deep understanding of the underlying technology, their query performance, database, networking, and build a custom sync engine around their product and their data.

Abstracting all of this complexity away in one general tool/library and pretending that it will always work is snake oil. There are no shortcuts to building truly high quality product at a large scale.

Damn. Here’s the upvote

Did anyone get a faster click speed than 45ms?

> think of your queries as super human friendly SQL > The database? Massive amounts of data boiled down to unique entries with probabilities. This is a simplistic, but accurate way to think of LLMs.

I disagree that this is the accurate way to think about LLMs. LLMs still use a finite number of parameters to encode the training data. The amount of training data is massive in comparison to the number of parameters LLMs use, so they need to be somewhat capable of distilling that information into small pieces of knowledge they can then reuse to piece together the full answer.

But this being said, they are not capable of producing an answer outside of the training set distribution, and inherit all the biases of the training data as that's what they are trying to replicate.

> I guess my point is, when you use LLMs for tasks, you're getting whatever other humans have said. And I've seen some pretty poor code examples out there. Yup, exactly this.

Good point. I'll fix this asap. I can imagine it can be annoying when you can't alt+click

Thanks a lot for trying it out and the feedback!

More formats are definitely on the roadmap. At first I'd like to add full support for higher order of spherical harmonics and then I wanted to take a look at other methods, too. Maybe 2DGS and/or SMERF would make sense for comparison purposes.

Explanation of controls makes sense, too. I'll add that.

Regarding WebXR, that's currently not on my roadmap. However, if the demand is there I'd consider adding it

Thanks a lot for trying it out and the feedback!

- Adding better controls (and an explanation) makes sense!

- Good job discovering the L control. That's actually something that's not supposed to be public. I use that tool to find the correct orientation of splats before publishing them. But once I find those values saved in the DB, there's no use for that tool anymore. When I make it available to the users I'll defo make the UX clearer.

- Good point about landscape mode. I'll fix that.

Thanks! At the moment the intent is to showcase what the method is capable (and what isn't).

One of my future plans is to extend it to other methods than just gaussian splatting so that we can compare methods across a wide range of captures with varying light conditions, different materials, etc..

100%. I really think Gaussian Splatting as a method can offer a lot, but it's also not powerful enough (yet) to be useful. Specifically editing and relighting GS models is rather clunky.

I think SplatGallery is an exploration of how people use the technology and what can it be useful for today and what is the next step.

I'm currently working on splatgallery.com. It's supposed to be a curated community driven gallery of the best 3D models reconstructed from photos or videos. It's currently in a very early stage and I am still adding more models to it hoping it'll gain traction from the community :)

Thanks! I was initially pondering calculating the moves on the server and storing the state regularly in the DB, so the animation can run forever. But in the end simplicity won and I just reset the animation every 24h. The cube is usually "as scrambled as it gets" after 20-30 moves anyway.

I'll defo take a look at playing the next song after the first one ends. I had this functionality at some point, so if it is not working it's defo a regression. Will fix it.

Btw, I am happy you love the music! It's royalty free music I added there, but I should add some credits as it seems many people listen to it. Since I published this last week it used up all my 100GB Vercel allowance and I had to move it to Google Storage.

Thanks for checking it out! Do you have some suggestions for a more interesting background? I was thinking about adding some planets/galaxies to keep it in the sci-fi and space theme.

And thanks for the bug report. I'll take a look at it this weekend!

I am based in London, UK.

And yes, you are right, Upwork can be a race to the bottom. Since I am based in a rather expensive city, I can't really compete with other developers on price, but I can still compete on offering, expertise, commitment, etc.. So far I managed to find enough clients who are willing to pay extra for a premium service.

Naturally, it also depends on the service you are providing. Luckily, my niche is not as saturated yet.

The other point with companies not willing to hire an individual is something I can relate to as well. And not only in regulated industries. It's mostly startups and small companies I work with at the moment.

I quit my job and became self-employed ~6 months ago. I work as a freelance developer and I focus on 3D graphics and computer-vision, but I occasionally take on other projects if they are interesting.

I find jobs on Upwork and I do cold reach out on LinkedIn and via email. So far, I managed to keep myself pretty busy and I landed a few pretty good projects. I consider that a success since I went into the freelancing world not knowing much about it.

It's hard, especially with the uncertainty of where the next project/money is coming from, but I can't imagine going back to a full-time employment anytime soon.

SEEKING WORK | London, UK | Remote

I'm a full stack software engineer. I have hands-on experience with machine-learning, especially computer vision and LLMs. I specialise in building websites and web experiences end-to-end also with the design, basically the whole package. But I am happy to jump onto ongoing project, too!

Any idea you might have, I'm happy to talk about it and I'll help you bring it to life :)

Tech stack of my choice: Python, Typescript, Next.js, TailwindCSS;

Currently, I am mostly looking for projects or contract work.

Website: https://www.martinpiala.com email: hello@martinpiala.com

Having an API with medical information is amazing!

Just out of curiosity, is a React client or even a javascript library on your roadmap?

I've been waiting for a tool like this for ages.

I see you link a jira ticket to a page. Is there a way to link whole Epics to Acreom page?

I could imagine an LLM that brainstorms all the edge cases, data modelling, algorithm, etc... The final decision will still have to be done by a human, but having a companion LLM that gives you ideas, plays devils advocate and looks for problems would definitely speed up the decision process.

It seems that the package calculates the lower bound of how much would it cost to write the same code with GPT-4. It does not take into consideration that even GPT-4 cannot write code at god mode and write it correctly on the first try.

However, it gets interesting when you realise that if writing the code with an LLM is dirt cheap, then 1000 iterations of writing the same code with the guidance of a skilled software engineer would still be cheap and probably faster. I can imagine a world where whole engineering teams are replaced by just one engineer with a code-generating LLM.

I recently started using the ChatGPT via OpenAI api. It seems to perform reasonably well on all tasks I needed it for so far. But bear in mind I use it for hobby projects so far.

I have not tried the open source LLMs so far as there's the additional hassle renting a server and deploying it there. Running it locally on a consumer GPU does not cut it yet as it is too slow. So to iterate faster, I prefer just using ChatGPT.

Oh this would be awesome. For very long time I’ve been looking for an unintrusive way to receive important notifications on time. And since I almost always listen to music this would work well.

In the UK it's £12.49 per year or £1.29 per month