I read a lot of comments talking about „getting down the operational costs“ but i am missing someone talking about the costs of depositing the nuclear waste until it has no more risks. Am i missing something?!

Yes the cost of depositing nuclear waste is trivial, it takes a small number of large concrete structures underground in well picked locations.

The US produces about 1250 cubic meters of waste per year. For comparison the empire state building has a floor area of 208000 square meters, assuming a 3 meter floor height you could fit about 500 years worth of spent fuel inside it.

Yes. This. Nuclear waste storage is extremely cheap.

Also, we only "use" 3% of the fuel in current nuclear power station designs so we could just reprocess the fuel and vastly reduce the volume of waste too.

SplatAM is an interesting new way to generate 3D Gaussians in real-time. It relies on RGB+D data and doesn’t need COLMAP at all. I am not related to it but am using it for a project with a robot, as its main purpose is to do SLAM. As far as I understand, it uses the point cloud for the alignment of the images

edit:typo

How does this work? Using 3d Gaussian Splats? Looks interesting!

The results i did get from deepseek-r1 on their webpage did not match the results i did get from o1-pro. I did ask it go to a github repo, find the part where the logic of the “export” button is and explain why it doesn’t work (the whole logic is actually missing, won’t work at all). O1 pro did get it right in the first try while deepseek r1 was heavily hallucinating. Maybe i am using the wrong model?

No, you’re not. They explicitly mention in the R1 paper (in the last paragraph before the bibliography) that R1 isn’t a “huge” improvement over DeepSeek-V3 in coding - where “huge” is an academic weasel word.

It’s just a lot of hype. In my coding tests it significantly underperforms o1 (haven’t tried o1-pro), often getting stuck in a reasoning loop because I underspecified something (that I don’t have to with o1).

Same anecdotal experience. Its definitely an improvement and they have made operational improvements at runtime but I am still concerned they are have over fit for the tests.

addictive

I learned today, that o-1 is able to search through all chats and can find and verify if the findings are relevant to the actual context. i found that very usefull as i have a lot of very long chats regarding only one project. ChatGpt lists the findings with the date and context and searches further back if asked for it. (in my case summer 2024)

Wait, how do you do that?

I did just ask to remember from our last chats, if we hadn’t this particular bug discussed before.

This method is promising, especially with flat and untextured surfaces. Secondly, this method has far better detailed results in the background. (compared to 3d Gaussian Splatting)

You are right, that many features in game engines cannot be used yet, especially relighting and reflections. But there are cases where game engines (like Unreal Engine 5) are used, for example in Virtual Production with Ledscreens, where a photorealistic background is needed (3d gaussians do look more realistic and are cheaper to produce than a comparable scene made of polygons)

Supersplat is actually a game engine (but for the web)

This looks like a promising tool to (also) generate completely generative 4d Multiviews which then can be used to generate 3D-GS, their pipeline also supports animated objects, camera zoom and pan. They do benchmark their results with 3D GS. The code is unfortunately not yet published, cant wait to try it. https://gen-x-d.github.io/

Thank you for releasing this. It is the first option afaik, to generate a 3D Gaussian on a Mac without a gpu (using M1 Pro). It is quite slow, but quick enough to test-train a dataset while onsite, without the need to carry heavy workstations around! I really like the option to use rerun.io for training analytics. Again, thank you.

You're welcome and thank you for trying it out!

Hard at work to make performance better - the "main" kernels are at least as fast as gSplat, so now need to remove other overheads.

That, and make splatting train more efficiently in general, lots of compute is wasted on small steps.

Ps: the web version takes a minute to warm up and is generally slower, do try a native version if you haven't yet!

Thanks for the advice, i did compile the repo on my m1 using vs code, but i do compare the speed to my workstation RTX4090, that comparison is not appropriate.