3D Gaussian Splatting for Real-Time Radiance Field Rendering paper page: huggingface.co/papers/2308.0… Radiance Field methods have recently revolutionized novel-view synthesis of scenes captured with multiple photos or videos. However, achieving high visual quality still requires neural networks that are costly to train and render, while recent faster methods inevitably trade off speed for quality. For unbounded and complete scenes (rather than isolated objects) and 1080p resolution rendering, no current method can achieve real-time display rates. We introduce three key elements that allow us to achieve state-of-the-art visual quality while maintaining competitive training times and importantly allow high-quality real-time (>= 30 fps) novel-view synthesis at 1080p resolution. First, starting from sparse points produced during camera calibration, we represent the scene with 3D Gaussians that preserve desirable properties of continuous volumetric radiance fields for scene optimization while avoiding unnecessary computation in empty space; Second, we perform interleaved optimization/density control of the 3D Gaussians, notably optimizing anisotropic covariance to achieve an accurate representation of the scene; Third, we develop a fast visibility-aware rendering algorithm that supports anisotropic splatting and both accelerates training and allows realtime rendering. We demonstrate state-of-the-art visual quality and real-time rendering on several established datasets.

How much edge compute is needed you ask? If you hard code your physics, control systems are surprisingly cheap. Inputs are a bunch of IMUs + altitude. At a rate of 400 / sec, that's ~ 64 KB / sec of input processing. Output is next to nothing. Could run on a Raspberry Pi easy.

Hate to dox myself a bit but have worked on just about every fighter jet the US has. I have seen some impressive technology over my career but this is a whole other level. I have so many questions and need to know how this works. How much edge compute is needed to make this happen? My first thought is dual processor + 1TB ram. That way it can handle the fuckquintillion process per second. There was zero correction it nailed it 100%.

Reverse Engineer Anything 😂 Software is done.

there is an argument (which I've made privately until now) that one of the principal innovations of the large language model labs is a *legal* innovation, not a technical one by building a system that hoovers up mind-bogglingly large volumes of human information and feeds it into a recombinatorial association machine, the companies have bulldozed the existing IP regime and made the contents of ~all human IP (including the most mundane) searchable, reconfigurable, and usable while also obscuring any trace of origin and eliminating a need to provide credit or attribution. much of the perceived benefit is therefore access and exposure to IP people would not otherwise have had access to, presented behind a system that abstracts the IP from its context and history and presents it as net-new information. I imagine we would have seen ~similar productivity outcomes had Google actually been allowed to make productive use of the Google Books database over a decade ago.

This is the doom I predicted a few days ago, coming for Photoshop. A clean-room open-source reimplementation. No prizes for guessing that they decompiled Photoshop to source code, processed that to some kind of non-code specification language, then fed the spec to an LLM with an instruction to generate Rust. Adobe just got nuked. And closed source is dead, dead, dead. github.com/storytold/photocr…

The end of software secrecy is almost upon us. The death of closed source, and the final triumph of open source. I should have realized this a few months ago when I successfully decompiled the game of Firefighter from an ancient DOS shareware binary. My robot friend was able to tell it had been written in Borland Pascal from looking at the data layout; it gave me back very readable Pascal code with sensibly chosen function and variable names. I transpiled it to Rust and now ship it as part of my heritage games collection. The thing is, I thought of this as a fun stunt but didn't have any confidence that the technique would scale up to large, real programs. I have since learned that people are now doing this sort of thing with entire AAA games, which are among the most complex software artifacts ever to be shipped as a binary. If they can be decompiled, anything can be. This has implications. Massive implications. We need to think about what the world is like when, in general, there is no longer a secrecy moat around almost any software at all. 1/2

Canned goods and ammunition

NEW: According to a bombshell report in the New York Times, Anthropic co-founder Chris Olah threatened to walk out of Pope Leo XIV’s AI encyclical launch in May because the pope rejected the idea that machines can be conscious. Olah’s team then privately lobbied the pope’s advisers “to take the possibility of model consciousness seriously.” Pope Leo XIV held firm. For months, Anthropic has wined and dined theologians and religious scholars under nondisclosure agreements, hoping they would bless the idea that Claude has moral standing. thelettersfromleo.com/p/nyt-…

Most people don’t yet grasp what is happening in France. Markets are pricing French sovereign debt as junk, rating agencies will eventually have to follow. This will have two major impacts: 1. Most French banks are already rated at or just below the sovereign, so a move toward junk would likely drag domestically focused lenders with it. Credit to households and firms would slow sharply, hurting the economy and widening the fiscal deficit even further, a vicious cycle. 2. For the ECB, the constraint is legal as well as financial. A fall below investment grade would force sales by ratings-bound investors while making any backstop harder to justify under current rules. The next euro crisis will begin in France. The first, which began in Greece, will feel like a walk in the park compared with what comes next.

Adam Neumann on why top-down management fails with great talent: "Top to bottom means you think because someone reports in to you, they have to do what you say." "But it's not true. This is not a dictatorship. They have free will." "If you hired someone, they're really talented, they'll go work elsewhere. The more talented they are, the more the top to bottom does not work. They won't be willing to do it. They shouldn't." "Great talent is not willing to be managed like this." "If you're gonna manage these employees and you wanna attract the best talent in the world, remember that power comes from influence, not control." "If you think they need to do what you said because you're their boss, you've already lost, and it's a matter of time till it doesn't work out. If they're okay with it... they're not the right employee for you, and you're not the right boss for them. There's no chance you're getting the best out of them." @AdamNeumann w/ @StevenBartlett