Hacker News: colingauvin

New comment by colingauvin in "Muse Spark Open"

colingauvin — Fri, 16 Oct 2026 18:47:43 +0000

I was running DS731 until Qwen 3.8 Flash Next (so what, like a couple weeks? The pace has been torrid). I switched to Qwen for image input, then GLM 5.3 Flash. At the time, Qwen felt like a minor step down from DS731, GLM 5.3 Flash feels like a major step up from Qwen, so I'd say slightly better than DS731. I realize that's not exactly what the benchmarks say, but DS731 definitely flailed around on some of the more challenging things that GLM mostly gets for me.

New comment by colingauvin in "Muse Spark Open"

colingauvin — Fri, 16 Oct 2026 18:44:56 +0000

I got this frequently with on GLM 5.3 Flash with GLM's actual plan, I do not get this with self hosting.

New comment by colingauvin in "Muse Spark Open"

colingauvin — Fri, 16 Oct 2026 18:43:18 +0000

Pretty much just this, but tweaked to have I think 64 active conversations be cacheable, which drops the context pool to ~2M.

https://github.com/MiaAI-Lab/GLM-5.3-Flash-EXL3-2x-DGX-Spark...

I also had to downclock my Sparks (Asus) slightly, to 2000 Mhz. Otherwise they'd overheat and crash.

New comment by colingauvin in "Muse Spark Open"

colingauvin — Fri, 16 Oct 2026 02:00:27 +0000

Yeah, MiMo Pro is the first Chinese model I can really clearly identify as an upgrade over GLM 5.3 Flash. K3, Qwen 3.8 Pro, GLM 5.3, DS4.1 Flash all feel around equivalent to me. Oddly lots of people have derided MiMo but I have found it able to tackle slightly tougher problems. For instance, I tried GLM 5.3 Flash, DS4.1 Flash, and MiMo Pro on making a new map layer for my Garmin watch, and MiMo was the only one that found the actual best method (.img file for OSM).

New comment by colingauvin in "Muse Spark Open"

colingauvin — Fri, 16 Oct 2026 00:59:27 +0000

It is unreal how good GLM 5.3 Flash is. There's an ~4 bpw EXL3 quant that fits on 2x DGX Sparks. I'm not sure it's worth it now ($7k/Spark) or even when I bought them ($4k/Spark) but there's something about knowing that the whole internet could go down and I could still have this model running at 50-60 tokens/s with 1M context, indefinitely. It's just so good. TensorFold hits 100+ tokens/s in aggregate with 2-3 M total context pool. It's like having Claude at home.

New comment by colingauvin in "Danish Supreme Court Finds That AI CSAM Is CSAM"

colingauvin — Fri, 16 Oct 2026 00:04:46 +0000

There's a few comments (boldly) criticizing the ruling for being technically incorrect. If no child was abused, how can it be a child abuse crime?

I would counter with this: If it is technically impossible to tell the difference between AI generated images, and real ones, how could anyone ever be prosecuted for having presumptive real ones in their possession ever again? Everyone tried would simply say "AI" and that'd be that, unless there was a victim to testify, or it was a case on generation of it etc.

So AI images of this nature do have victims, just slightly less directly.

Another adjacent question: How would you feel if it was an AI generated image of a specific child. What is the precise threshold of victimhood that is necessary?

New comment by colingauvin in "Why aren't AI companies being charged for hacking?"

colingauvin — Mon, 12 Oct 2026 15:10:51 +0000

You can jail the actual pedophile in that scenario, you cannot jail an agent. The real question is whether the person who instructs the computer to do the thing that leads to hacking should be liable, or whether the company that made the tool that when used unsafely lead to hacking should be liable. Gun manufacturer's typically are shielded from liability. They also have a lot more disclaimers on their products though.

New comment by colingauvin in "How did Rosalind Franklin miss the helix in her iconic DNA image? She didn't"

colingauvin — Thu, 08 Oct 2026 04:38:35 +0000

Technically beta keratin is helical. That said you are correct, there is no requirement to be helical for fiber diffraction. It just turns out it's very difficult to have non helical uniaxial symmetry in nature.

When I was studying spindle shaped viruses by electron microscopy we'd get beautiful fiber diffraction patterns in the fourier transform of the micrographs. I always wanted to try and solve the helical parameters but never got around to it.

New comment by colingauvin in "How did Rosalind Franklin miss the helix in her iconic DNA image? She didn't"

colingauvin — Thu, 08 Oct 2026 04:29:32 +0000

Specifically the antiparallel base matching was the important bit, agreed, but minor nitpick. The first alpha helix wasn't solved until 1951, so one year earlier. Their ubiquity was very novel.

New comment by colingauvin in "Local AI is real now. And it's blowing my mind"

colingauvin — Wed, 07 Oct 2026 04:22:10 +0000

The author's configuration is..... Interesting.

I don't disagree with the title. This spring folks were saying "I use Qwen 3.6 27B (or 35 A3B) as a daily driver". They either had low standards or were lying. The models were good enough technically, they capable enough, that you could see the potential, but the coherence was really not great compared to frontier. They'd lose track of what they were doing, mix things up, etc. Technical ability definitely arrived before coherence.

Then DeepSeek 4 Flash came out and suddenly it was like... Ok. You can run a local model that keeps coherence, and is decent technically. Then we got a rash of models that are both good technically and coherent: DS4 Flash 0731, Qwen 3.8 Flash Next, Qwen 3.8 27B, GLM 5.3 Flash, Hy4, MiMo 2.6 Flash... It just has no stopped. We have definitely crossed the threshold from interesting to very usable.

I like the solar bit. Not sure why the author is using a 4 model setup. My tests with Qwen 3.8 have convinced me it's completely fine general purpose, and dedicated small/vision/etc are useless. I can get 110 TPS single stream on 2x Sparks, with 5M total context, concurrent I think some folks are hitting 200-250 TPS. There's no reason to use anything else right now, it's really remarkable. For an Opus 4.6/4.7 quality model.

I am eagerly awaiting the release of Qwen 4 Flash.

New comment by colingauvin in "California closed the Montana license plate loophole"

colingauvin — Wed, 07 Oct 2026 00:27:59 +0000

I certainly don't pay $25 to register. Maybe it's different for businesses? But for me on a 2024 truck it's $300-$400/year in Montana.

New comment by colingauvin in "VeloGB10 – A GB10-specific inference engine"

colingauvin — Tue, 06 Oct 2026 02:40:38 +0000

Not my project but wanted to share. My 2x Spark config with Qwen 3.8 Flash went from 37 tps to ~90 tps (prose). It's running phenomenally well and really impressive.

VeloGB10 – A GB10-specific inference engine

colingauvin — Tue, 06 Oct 2026 02:40:38 +0000

Article URL: https://github.com/sf-stav/veloGB10

Comments URL: https://news.ycombinator.com/item?id=49973521

Points: 2

# Comments: 1

Primitives for Sane Conversation About AI

colingauvin — Mon, 05 Oct 2026 01:13:27 +0000

Article URL: https://humanparadox.org/primitives-for-sane-conversation-about-ai/

Comments URL: https://news.ycombinator.com/item?id=49959663

Points: 1

# Comments: 0

New comment by colingauvin in "Seattle City Council votes to ban surveillance pricing in sale of groceries"

colingauvin — Wed, 23 Sep 2026 17:41:14 +0000

Not comparable. The markets can still charge wherever they want, but it needs to be priced per item and not per customer. In your house counterexample, you could set whatever list price you want.

New comment by colingauvin in "OpenAI is enlisting an influencer army to make it look 'good for the world'"

colingauvin — Wed, 23 Sep 2026 16:11:38 +0000

Thanks for sharing. Very interesting.

New comment by colingauvin in "OpenAI is enlisting an influencer army to make it look 'good for the world'"

colingauvin — Wed, 23 Sep 2026 14:45:55 +0000

Could you share more about this?

New comment by colingauvin in "The new CC, an AI agent built for families"

colingauvin — Wed, 23 Sep 2026 01:45:11 +0000

I tried to connect Claude to my Google workspace calendar and email and tasks. Calendar and email no problems. But no public Tasks mcp server seems to exist. I'd have to host my own.

New comment by colingauvin in "Pentagon says overreliance on AI contributed to missile strike on Iran school"

colingauvin — Tue, 22 Sep 2026 22:20:05 +0000

>people that decided to shift a significant weight of decision-making authority to an AI

And I hedged that. Anything short of 100% responsibility with humans is a failure. I get investigating how it occurred, but that needs be very careful to separate ought from is.

New comment by colingauvin in "Meta bans ads for Virginia Woolf play in Spain"

colingauvin — Tue, 22 Sep 2026 20:58:10 +0000

1) HN guidelines explicitly forbid astroturfing allegations:

> Please don't post insinuations about astroturfing, shilling, brigading, foreign agents, and the like. It degrades discussion and is usually mistaken. If you're worried about abuse, email hn@ycombinator.com and we'll look at the data.

https://news.ycombinator.com/newsguidelines.html

2) Not part of the ruling class, my life is somewhat well documented on my blog. Just an average dude at my computer.

3) https://novelteesgifts.com/cdn/shop/files/it-has-come-to-pas...