pkroll

Since no one else posted it... I have open-webui pointed at a linux box with 128 gig of ram and an RTX Pro 6000, and after a couple of runs on trivia, had it do one of Open WebUI's conversation starters: "Show me a code snippet of a website's sticky header in CSS and JavaScript."

72.06 t/s. That's the full Qwen 3.6 27B model BF16, using MTP, running on Ollama. Yes I know I should bite the bullet and get vllm running on that box.

That was, also, at a 570 watt limit: I normally run a little less, but when I first tried this I actually forgot I had set the limit to 300 (it's a hot day, I figured why fight the A/C?), and at 300 watts the same question came back at 69.38 t/s. (The extra power matters more for compute bound things, the difference in generating LTX2.3 videos is considerably higher... but still not linear.)

Check the LLM benchmarks once it's out: it's such a common use case for these kinds of machines, you won't be waiting long.

If this pans out, you're not at all kidding: https://www.youtube.com/watch?v=8ekndZwyOzo

Really? Why? I'd bet the opposite: the worst of the things happening with OpenClaw aren't being revealed.

Not a shareholder, but on first try, it won't do it because it recognizes Iger's name. And clearly the deal is fresh because it balked at Mickey Mouse too. But it has no trouble with just, "mouse": https://sora.chatgpt.com/p/s_693ae0d25bbc819188f6758fce3f90c...

It's likely that I'm seeing this from my deep into ComfyUI bubble. My impression was that AUTOMATIC1111 and Forge and the like, were fading as ComfyUI was the "what people ended up on" no matter which AI generation framework they started with. But I don't know that there are any real stats on usage of these programs, so it's entirely possible that AUTOMATIC1111/Forge/InvokeAI are being used by more people than ComfyUI.

Did you test some local image gen software in that you installed the Python code on the github page for a local model, which is clearly a LOT for a normal user... or did you look at ComfyUI, which is how most people are running local video and image models? There are "just install this" versions, which eases the path for users (but it's still, admittedly, chaos beneath the surface).

Mass shootings in the US, are a little over 1 a day. School shootings are a subset, and as cudgy says, so far 13 this year.

"NTSTC content at 23.976 I'd hope the player would just speed up at that point, but even if not... judder at 120 Hz is better than at 60 Hz."

I'd bet money when TVs are advertised at 120 FPS, they're really 119.88 FPS, so no judder showing 23.976 FPS and the other NTSC-off display rates.

It's a regular expression, and OS/2 was referred to in many ways, so try something like: "os-2|os\/2|os2" (without the quotes)

I get 136 results, from that query.

Well, they sort of do: they keep referring to the 4090, on their Github and primary promotional pages (https://wan.video/).

But really all the various video models really want an 80+ gig vram card, to run comfortably. The contortions the ComfyUI community goes through to get things running at a reasonable speed on the current, dinky-sized vram consumer cards, are impressive.

As jasonjmcghee says, they're available... but if you go to ollama.com and set models to "newest" you'll see Mistral (specifically mistral-small3.2 at this writing) because they seem to not sort the models based on newest update: only newest "group" or however you'd phrase it. So you need to scroll down to "qwen3" to see it's been updated.

Slightly frustrating. But good to know.

https://arxiv.org/abs/2412.10849

"Our study suggests that LLMs have achieved superhuman performance on general medical diagnostic and management reasoning"

I use Markdown Viewer, in Chrome: I'd bet there are multiple equivalents in Firefox and Safari. Well. I don't know what Safari's extension universe is like but it seems likely.

You're not the only one thinking that: https://www.nvidia.com/en-us/project-digits/

128G of unified memory. $3K. Throw ollama and ComfyUI on that sucker and things could get interesting. The question is how much slower than a 5090, is this gonna be? The memory bandwidth isn't going to match a 512 bit bus.

That's too simple a comparison, against something that's a little more complicated. A 720p stream without adequate bandwidth can have terrible artifacts, mostly showing up during fast motion/panning/action. They can look objectively worse than DVDs.

I don't get it: the new models still need to be used somewhere, unless you're coding everything yourself, and that means they'll mostly get used in the updated ComfyUI nodes that work with the new checkpoints and LoRAs (and are available today).

Well, MS isn't fatal, but it certainly doesn't HELP... people with it have a generally shorter life expectancy (by like 7 years) from complications with something else, like heart disease or cancer.

None of which takes away from it being terrible that we've lost Terri Garr.

The "fixes your colorblindness" glasses don't work, and they're still a thing.

Worked with a lot of directors on their first or nearly first movies, like James Cameron, Martin Scorsese, Francis Ford Coppola, Peter Bogdonovich, Ron Howard. Even the Fantastic Four movie he produced had some pluses (the Red Letter Media review is worth watching).

For anyone who hasn't gotten into the coffee insanity yet, he doesn't mean his friend literally gives the coffee acupuncture... but a cork with some acupuncture needles (or a device that looks like such) is commonly (!) used to stir/even out/redistribute/break up clumps of coffee in the portafilter before tamping. And reading that I now need to go get some coffee.

Oh, THAT's pretty? I give you the Manument: https://manument.com/en/manument-leva-machine

Well. Not GIVE. It's $20K.

Not just dropout: the disc stacker will set each pixel to the median (if there are enough copies) or an average (if there are just two) so even slightly off pixels on one disc of three, will be caught/fixed. (You can do the same thing with VHS, but not with their stacker software. You'll need to resort to VapourSynth or Avisynth/Avisynth+.)

"...our very expensive grinder." To save you the effort: that's about $4300 of coffee grinder, in that video. (Weber EG-1, Black. White is $400 "cheaper.")

It's not ever illegal, as long as it's your physical copy. Is it unethical? Well if you're censoring your copy, clearly not: you still saw the ads.

But are you asking in good faith? Or are you asking because you want to get to a point where you use a service that costs money to maintain and yet you don't spend money or view ads but you still feel ethical?

No: but the ads ARE THERE. They're actually in front of you. Not so with an ad blocker.

I'm with nickthegreek: I hate ads, but YouTube saying you can't make use of our service without paying or seeing ads isn't bullying.

We need more languages, not fewer. We need all the experimental languages, the attempts at solving issues at the language level, to get to the next Good Language. We've got plenty of Good Languages right now, but we don't get others without a LOT of little languages getting made and inspiring the next ones.

Why is "of a radical nature" the important part here, and who gets to define it? Is fuel injection radical? Seatbelts? Crumple zones? GPS? In 1909 a car had 35HP and could peak at 53MPH, and was an ultimate death trap in an accident. Hundreds of improvements, some more radical than others, led to the cars of today being better in virtually every way, including subtle ways nobody knew mattered at the time (like not flinging people out the windshield in an accident).

I'd be happy to see 24fps die. You said HFR shots "just look like real life" and to me that's precisely what any form of video SHOULD start with. You want to make an artistic choice, fine, but can we start with as crisp, clean, color rich, and highest frame rate possible please, and change those if the director or cinematographer think it'd be best to do so?

Yeah: I'm one of those folks with Motion Smoothing On on my expensive TV. 24fps is a remnant. A slideshow. You're conditioned to like it from having seen it for years, but it's not in any way special. Let. It. Die.