Slava Gilevich

Building next-gen QA tools for the Cursor age @qalti_ai

[Slava Gilevich @__int32]

Grok 4 vs GPT-5 as a mobile qa agent: Grok 4 matches GPT-5 in general-purpose UI interactions, and completely beats it in 3D space understanding

[Slava Gilevich @__int32]

@yacineMTB My third fluid sim:

[Slava Gilevich @__int32]

@DylanMcD8 Here’s my app clip for 3D hypersonic wind tunnel simulation (runs on your phone). You can use any 3D model to check its aerodynamics, or just cook in the rocket exhaust:)

https://t.co/bfg9bi2JMA

[Slava Gilevich @__int32]

@SebAaltonen Should’ve been named copy_cubemap.wgsl:)

[Slava Gilevich @__int32]

@FrameworkPuter @AIatAMD Mature? Yeah, sorry, no. Spent 2 weeks trying to port Qwen3-TTS to RyzenAI NPU runtime with every possible trick I know to no avail. @LisaSu can you at least bump the open-sourced version with new kernels?

[Slava Gilevich @__int32]

@gleb_alexandrov it's not a synthetic data, they collected their own dataset using sodium light and sodium light filter in a prism: https://t.co/TtV3W1REnj

[Slava Gilevich @__int32]

@anemll Amazing! I was hoping to squeeze at least 1tps from M1 Ultra 64Gb, but hit a wall at 0.1tps due to preloading going into swap and messing things up. Will try to do a direct read from SSD this weekend.

[Slava Gilevich @__int32]

@eugenebokhan And two chips that support cooperative tensor properly are m4 and m5, yes? Other chips ‘support it’, but only two latest apple chips gain actual acceleration with cooperative tensors?

[Slava Gilevich @__int32]

@styropyro_ @Winterrose Nobody: …
Styropyro: boy, do I love the smell of fresh Helium-3 Z-pinched plasma in the morning!

[Slava Gilevich @__int32]

@ManyATrueNerd This is exactly how the current AI works. It spews out perfectly written code, paragraphs of in-depth on any topic, but when you look inside, it’s just a bunch of math, and nobody reeeally knows why and how it works.

[Sergey Gonchar @gonchar]

We’re excited about our upcoming partnership with Razer! The companions are now physically on your desktop! They can see, hear, and speak with you, and even see your screen.

[Slava Gilevich @__int32]

@Luckyballa My solution in the MLS-MPM implementation is to use sort + atomic. I have a case when I need to scatter over 3x3x3 cube of voxels. The sort improves data locality a lot, and atomics outperform 27 scatters with later reduction over 27x data

[Slava Gilevich @__int32]

@Nick_Davidov That’s why UBI won’t work

[Slava Gilevich @__int32]

@Nick_Davidov There is another factor to this. With extremely high housing prices and 30-50 year (!) mortgages, you are almost forced to think in terms of stable income, and you have to have at least half a year in savings to afford any experiments of making something yourself.

[Slava Gilevich @__int32]

@Nick_Davidov School/uni makes a huge bias towards avoiding failure at all costs, and making things is risky.

At least, it made in my case, and I’m still beating this crap out of me.

[Slava Gilevich @__int32]

@OpenAI NGL, nano banana is better

[Slava Gilevich @__int32]

@RoszykAdam Did tou get access to camera stream, or images are loaded from the iPhone?

[Slava Gilevich @__int32]

@lisyarus You want to add earth rotation effect, where atmosphere has a slight movement from west to east , and it would generate vortices after land masses, aka hurricanes:)

[Slava Gilevich @__int32]

@ZoldenGames For a few particles more

[Slava Gilevich @__int32]

@Luckyballa @ionthedev I’ve always thought that you can just convert Gaussian splats into SDF with zero being some variable threshold, so that the big splats result in larger volume?

[Slava Gilevich @__int32]

@twominutepapers Here’s implementation of the similar approach (bar the whirlpools), a full blown MLS-MPM running 60 fps at 1M particles on my iPhone!