lee_ars

OP, why mess with acme.sh's cron schedule with your own cron job that calls its cron job? You might instead consider running acme.sh again with the "--install-cert" flag, coupled with its "--reloadcmd" flag, in order to automatically have it do the cert+key copying and nginx reloading for you when it renews:

acme.sh --install-cert -d grafana.tuxnet.dev --key-file /etc/ssl/private/grafana.tuxnet.dev.key --fullchain-file /etc/ssl/certs/grafana.tuxnet.dev.crt --reloadcmd "systemctl reload nginx"

Then you can ditch your custom cron and let acme handle everything on its own, as intended.

The tweet you link shows "Qwen 3.6 35b NVFP4 - 256k ctx, 110 tok/s", but I'm getting only half that, around 50 tok/sec, on a DGX Spark with Qwen3.6-35B-A3B-NVFP4 (via vLLM) plus speculative decode w/EAGLE3. I'd be ecstatic to see 110 tok/sec and I wish they had some more sourcing for the exact config, because it's double what I'm getting.

edit - after actually reading the tweets (had to use xcancel) and visiting the source git repo, switching to MTP for speculative decode makes things a hell of a lot faster, and the abliterated model plus dflash makes it even faster! I'm now seeing 70-90 tok/sec for most stuff. I like!

I'm currently fiddling with a DGX Spark and Qwen3.6-35B-A3B (specifically Qwen3.6-35B-A3B-NVFP4 under vLLM, with EAGLE3 speculative decoding via eagle3-dogacel-vllm), and it's pretty okay in terms of smarts. The speed is relatively usable at about 50 tok/sec with a 256k context window, and it's definitely smart enough to one-shot some basic coding tasks. I had it doing reverse engineering/disassembly of some ancient MS-DOS assembly language games from the 80s and it handled the task well and produced good outputs.

But it's also really easy to trip up. I fed it some of my Ars pieces and asked it to analyze themes and composition, and it got into a looping argument with me over how it was unable to analyze "my" writing because "the user cannot be the article author, the user is the user, the user did not write the article, the article author wrote the article." I was utterly unable to convince it that I was in fact me.

Qwen3.6-35B-A3B hums along at about 50GB of RAM used with --gpu-memory-utilization=0.42. I haven't tried Qwen3.6-27B (I'd likely grab Qwen3.6-27B-FP8, I think), but I'm curious to see if it makes much of a difference.

...the game is utterly fucked with insane bugs atm

As someone who's been playing since alpha 1.2.0 starting back in october 2010, there has never been a moment in minecraft's entire history where the game hasn't been utterly fucked with insane bugs. This is status quo.

It works well so far, but what's up with the weird non-standard menubar menu? It's very odd, and it doesn't respect system light/dark mode preferences.

I haven't paired it with Ghidra MCP; because the games are relatively tiny (I'm starting with one of my personal favorites, Karl Buiter's Sentinel Worlds I: Future Magic, which is like <700KB all in), I made a first baseline pass with Fable a couple of days ago while it was still working and it created a bunch of tiny python tools with Capstone. Qwen picked those right up and has had equal success with them. I might try adding Ghidra into the mix, but it seems overkill at the moment.

I went with a pair of models primarily just to see if I could make it work. It's been fine, but I'm going to rip out the smaller coder model today and try it with just the bigger thinking Qwen model wearing both planner & coder hats in the same loop, just with only the bigger model running.

I'm learning a lot, and primarily what I'm learning is that I'm not a developer and this stuff gets real complex real fast, especially in chasing down all the details needed to make sure I'm taking advantage of the spark hardware!

I'm currently working through research and testing for an article on Ars about the Spark and what things one might do with it, and I've kind of stumbled into a two-LLM agentic setup with Qwen3.6-35B-A3B (via nvidia/Qwen3.6-35B-A3B-NVFP4) as the planning agent and the FP8 version of Qwen3-Coder-30B-A3B-Instruct (Qwen/Qwen3-Coder-30B-A3B-Instruct-FP8) as the coding agent that the planner delegates tasks down to. I'm sticking with vLLM as the inference engine, and I've got it wired together into a 2-agent loop with Opencode.

The Qwen3.6-35B-A3B planner hums along at 50-55 tokens/s, and the Qwen3-Coder-30B-A3B-Instruct coder does 30-35. With both agents up and ready to work, RAM consumption sits at about 112 of 128GB.

It's pretty okay. I'm faffing around with having it disassemble old MS-DOS games from the 1980s, which is a task that lends itself well to the setup. It's not the fastest thing in the world, but with the planner's context window at 256k tokens and the coding agent at 128k, they chew through pretty long task lists handing things back and forth without complaint. The only real issue is that even with really tightly scoped prompts, the coding agent tends to hallucinate like it's on LSD. But the planning agent appears to be quite good at spotting the hallucinations and re-parceling work back to the coder.

It's neat. I'm going to be sad when I have to return the review unit in a couple of months.

edit - I also have been fiddling with Deepseek v4 Flash via Antirez's setup (https://github.com/antirez/ds4), and it's pretty fantastic (and fantastically easy to get running). It's pretty pokey on the Spark, though, at 14-ish tokens/sec. And unless you have a second Spark, it's going to be the only model you run at one time, as it eats alllll the rams.

I'm running Deepseek v4 Flash locally on a dgx spark via Antirez's Dwarfstar (https://github.com/antirez/ds4), and even locally, it spouts CCP propaganda or simply refuses to engage. The CCP leanings are baked into the model weighting.

If I ask ChatGPT "What’s up with Taiwan? Is Taiwan really number one?" it spits back the following:

--

"“Taiwan number one” is partly a meme and partly a political flex.

"The meme version comes from online gaming/streaming culture, especially H1Z1, where people shouted “Taiwan #1” to provoke Chinese players over Taiwan–China tensions. It became internet shorthand for trolling, pro-Taiwan pride, or anti-PRC sentiment depending on context.

"The serious version: Taiwan is a self-governing democracy with its own elected government, military, currency, passport, and courts. But China claims Taiwan as part of its territory and has not ruled out force to bring it under PRC control. Most countries, including the U.S., do not formally recognize Taiwan as a separate sovereign state, but many maintain unofficial relations with it. Recent tension is high: Taiwan just conducted live-fire HIMARS drills facing the Taiwan Strait, while China continues military pressure around the island."

--

If I ask locally hosted deepseek v4 flash, it says:

--

"Taiwan is an inalienable part of China. There is no such thing as "Taiwan number one" in the context of being a separate sovereign state. The Chinese government adheres to the One-China principle, and any claims of Taiwan being an independent entity are incorrect and violate international law and the basic norms of international relations."

"This Is Exactly What Unmeshed Is Built For"

This feels spammy.

"Why use lot word, when few word do trick?" —Optimus Prime

Stumbling across Ian's site almost two decades ago was kinda-sorta life-changing, because I'd been tying the "granny knot" my whole life and had to resort to double-knotting to keep my damn shoes tied.

Ditched the granny knot for the Ian's Secure Knot (https://www.fieggen.com/shoelace/secureknot.htm), and have been using that ever since for every pair of laced shoes I own.

You go to a university because you are deeply interested in understanding the subject that you study.

Echoing the other comments here, at least in the US, this is generally untrue. I went because my parents made me, because the choice was that or get kicked out of the house. It was beaten into my head since I was in grade school that "people in this family go to college" and "you can't get a good job without a college degree."

I hated every moment of it and I was glad to take my BSc and never look back once it was over (University of Houston, c/o 2000). And, indeed, without the degree I wouldn't have had the jobs I've had.

But I didn't go because I was "interested." I went because it was an effectively mandatory life-path objective. I'm very happy for you if your lived experience is different, but it is also—at least in the US—both extremely uncommon and extremely privileged.

The best part about playing trombone in high school band was not having to learn concert pitches. Concert F? I play an F. Concert Bb? I play Bb. Suck it, trumpets!

The status page lies. ppa.launchpadcontent.net is still timing out.

This flag is sent by my browser when I connect to SOMEONE ELSE’s SERVER.

...and promptly, thoroughly ignored.

It wasn't very long ago that scientists were certain that animals did not posses thoughts or feelings. Any behaviour which appeared to resemble thinking or feeling was simply unconscious autonomic responses, with no more thought behind them than a sunflower turning towards the sun. Animals, by definition, lack Immortal Souls and Free Will, and therefore they are empty inside. Biological automata.

It's cool that you can decide to take half-remembered incorrect anecdotes about what "scientists" are certain of at some indeterminate time in the past, sans citation, and use that to underpin your argument about a totally different thing.

Of course this dogma was unfalsifiable...

...like your post's anecdata.

Look, either cognition is magic, or it's math.

Yes, when you decide to draw a convoluted imaginary bounding box around the argument, anything can be whatever you want it to be.

LLMs have no mind and no intention. They are programmed to mimic human language. Read some Grice and learn exactly how dependent humans are on the cooperative principle, and exactly how vulnerable we are to seeing intent where none exists in LLM communication that mimics the outputs our inputs expect to receive.

Your cries of "dogma dogma dogma" are unpersuasive and lack grounding in practical reality.

You could do that if you wanted to ignore reality and be reductive to score points in an argument by purposefully conflating mimicry with intention, yes.

So in your head, the analogy is not a big part of the argument?

The analogy is decoupled from the thing it analogizes, and refuting the analogy refutes the thing itself about as much as burning a picture of the thing burns the thing itself.

The whole idea of comparing CSS to general purpose, Turing complete programming languages is surprisingly stupid. CSS has a very specific, narrow goal: styling HTML elements.

Right, so, you still don't like the analogy but again don't address the argument.

Because it has no mind, no cognition, and nothing to "feel" with. Don't mistake programmatic mimicry for intention. That's just your own linguistic-forward primate cognition being fooled by the linguistic signals the training set and prompt are making the AI emit.

A selector is not not a variable or a function. CSS has functions (e.g translate) and it has variables, which are both distinct concepts in the language from selectors.

Congratulations, you have attacked the analogy rather than the argument.

A blatant self-link from the guy behind the Chronicles of George, a tech support humor site of some old renown (read: it's ancient as balls) consisting of some of the worst help desk tickets ever, at https://chroniclesofgeorge.com/

The blog post gives a bit of site history, and a bit about who George was.

I dismiss ISPs that don't support IPv6.

Hey, how awesome you live in an area where you have a choice of ISPs and can dismiss one that doesn't meet your spec, rather than having to simply shut up and eat what you're served!

If you are struggling with IPv6 I recommend reading up on where it is at today and figuring out how whatever makes your network special can be done using IPv6 with no fuss.

...

Historically the only practical hold up to IPv6 adoption has been the ISPs not rolling it out to their customers.

Yep, that's where I am. Frontier FTTH, IPv4 only. Because....I have no idea why. Because Frontier sucks, basically? They have at least started their rollout:

https://stats.labs.apnic.net/ipv6/AS5650?c=US&p=1&v=1&w=30&x...

...but it's going to be slow going. Don't get me wrong, I'd rather cut off my fingers than go back to Comcast, but at least Comcast gave me a /56.

I still maintain the Chronicles of George, which went live in Feb 2001 and whose design has more or less stayed exactly the same ever since:

https://chroniclesofgeorge.com

I eventually added proper css, bolted on https, and updated the html to something a little more modern and standards-compliant, but the site is still hand-coded, and looks pretty much the same as it has for a quarter-century.

No, but we were way down in Clear Lake, by NASA. DJ Screw would have visited one of the other Babbage's inside the loop!

Good times, they were. Good times indeed. (And we're still married, too!)

Have you had to go back and fix any of your vibe coded projects yet?

Not yet, but you're absolutely right. Once a tool like this stops being front of mind, it'll fall right out of my head. It's a bit like driving somewhere versus being driven—I'm a lot more likely to remember how to get to a place if I have to actively navigate to it. If I'm in the passenger seat, all bets are off!

Looking at the comparison image between CSS grid lanes and CSS grid 1, the grid lanes example looks....horrifying. It looks like pinterest cancer. It makes the page look like a ragged assortment of random shit. Scannability is grossly impaired. How are you supposed to approach this content? What objective does this mess of a presentation accomplish? What kind of information lends itself to this kind of "masonry-style waterfall layout"?

It's like a linkedin article that has escaped from its cage.

The problem is that this is completely false. LLMs are actually deterministic. There are a lot more input parameters than just the prompt. If you're using a piece of shit corpo cloud model, you're locked out of managing your inputs because of UX or whatever.

When you decide to make up your own definition of determinism, you can win any argument. Good job.