cthalupa

It (Particularly ApoB/Combining LDL-C and Lp(a) is one of the single largest leading indicators of health risk we have.

If anything, the data we have is suggesting we've gotten wrong what the upper limits should be for what is considered OK.

https://www.lipidjournal.com/article/S1933-2874(25)00317-4/f...

Low cholesterol production is an extremely serious condition.

This is correct, but not in the way you mean it. We know people can effectively produce no LDL cholesterol in their liver and have positive health impacts - these MR studies are a big part of what drove this entire class of cholesterol medications. And the monoclonal antibody versions of PCSK9 inhibitors have shown basically the same results.

Virtually all human cells can produce cholesterol locally de novo, including your brain.

The problem is if DDR4 was viable here it would also be absurdly expensive. There’s no world in which we survive this demand without a corresponding increase in supply. It’s not like there are zettabytes of spare cheap DDR4 sitting around.

I snagged my two 4tb acer variants for under 4k each. CDW still has them listed for close to what I paid.

I’ve got a 128gb m5 max mbp and two sparks. For my real-world use cases, a single spark running DS4 Flash will have fully responded by the time my Mac has even started generating tokens. I figured I’d have more generation heavy work when I also bought the Mac, but it has done very little work running LLMs since I got the first Spark.

I mostly run them clustered for DS4 and am quite happy with the performance, and the cost isn’t that much more for two than the MBP while giving me double the unified memory.

I’ll probably pick up a third to run multiple smaller models. I don’t understand why people would buy a halo over a spark at comparable prices, particularly because if you want to cluster, the cx7 be beats the shit out of them when it comes to latency and throughput

Plenty of demand outside the US. Why would the hyperscalers not buy the chinese RAM for all of their datacenters across the world besides the US one?

Rising supply from China will impact prices even in countries where there are tariffs.

Anything where you're dealing with a large volume of records/documents. Lots of people are using these for large-scale digitization of documents - scanned stuff being OCR'ed and summarized, generating embeddings, etc. Large scale translation.

Anywhere where you might have a large backlog of data to work with can end up in this sort of situation.

The cuda cores can be broken up into compute complexes which larger blocks of memory directly attached to the cores.

Perhaps in theory, but for the gb10 stuff the memory is all on the CPU die and connected to the GPU die via nvlink-c2c

The dgx spark is the same chip and those are in the low 3s to 5 range for most of them depending on manu, storage config, etc. The dgx sparks also have connectx 7 cards in them to support the 200gbps networking for RoCE.

So I would expect the mini PCs to come in less than the sparks. Laptops I assume will be close in price with the addition of all the other laptop stuff.

Prefill is another advantage vs. Apple. It's way way way way faster on a spark than it is even on an m5 max.

Same model, same quant, same query, as close to as matched settings as I can get from vllm, and for workloads with large prompts + low cacheability, one of my sparks will often be done responding before the mbp is done with prefill.

Not true. This is aimed squarely at the Strix Halo and Mac markets. It's basically just strictly better than the Strix, and it's not clear cut vs that Macs in any sort of blanket statement.

My M5 Max 128gb MBP decodes faster than one of my Sparks, but the Spark's prefill is so much faster it can often answer the same query before the mac's prefill is finished. If you have large prompts, low cacheability, etc., a spark might be a very good options.

Not to mention you get can get two sparks and the MBP will be 85%+ of the cost at half the RAM.

I'm kind of tempted to pick one up. Leave running big models to my dual dgx setup, and all the misc. random stuff on an rtx.

For these in specific, they appear basically transparently to the GPU. There's a lot of software/firmware stuff for this, but also a different hardware architecture - while the RAM is on the CPU die, the nvlink-c2c gives it extremely low latency and 600GB/s bandwidth between the GPU and CPU.

If I see code like the one above posted by the OP, that the author wouldn't have written, I start to pay attention.

Except the author did write it. https://github.com/RsyncProject/rsync/issues/959#issuecommen...

Which is part of the problem with all of this nonsense right now - everyone is running off of emotion and not looking to see if what is being said is actually true. Which is somewhat ironic, considering the message of the article.

Never had this issue with any of my MBP. I never even have magsafe available, couldn't tell you where a USB-C to magsafe cable is in my house if my life depended on it.

There are a variety of inference engines that support this, regardless of whether or not there is native FP8 in Ampere - llama.cpp will do it quite happily. VLLM you can do W8A16 quant too.

There are a whole lot of ways to quantize models in general.

I remember getting my first CalDigit TB dock and being excited - everyone seemed to love them. I expected it to largely Just Work.

That thing Didn't Work more than it Worked, but options were slim. Eventually it fully died about 14 months in. I didn't even bother checking to see what the warranty terms were. TS3 Plus, back in 17 or 18. What a piece of shit.

Sounds like it's a good thing I didn't bother trying again in the early 2020s and only recently bought a new dock.

You can split tensors across an AMD GPU and Nvidia GPU - different architectures are not an issue. People run LLMs across some pretty crazy setups.

I've had multiple X520-DAs in desktop cases for years without doing anything special for cooling. Hell, one of them was in a fully watercooled system that had very little in-case airflow.

To the best of my knowledge, the Indian support teams for AWS have all the same access their US/EU/etc. support teams have when it comes to escalation and communication avenues. Obviously real time communication is harder for them than the US counterparts speaking to teams in Seattle, but the same is true for a team in Ireland or Australia.

If you are building a follow-the-sun support organization for a technology company, would you really avoid building a support team in India? Seems like it's the country most likely to have a large enough number of people with the expertise and language skills to staff for the need, even if you were paying them the same as their US counterparts.

From talking to people I know on support teams at hyperscalers and other tech companies: A mind-boggling huge portion.

But even as an AI believer and thinking it's great for this sort of thing, I also think if it's good enough for this sort of work, it should be good enough to identify when it's not capable of providing value, too.

You have a minority view on this argument, though. Scientific and structural realism both reject the idea that math is just a map. You've got company with the instrumentalists and antirealists, but the majority consensus is that math is somewhere between the structure underlying the territory to all the territory.

Zero was already part of the territory. Lack of something is a very normal state in the universe. Once we added it to our understanding of math, we were discovering it, not creating it. Of course people who are scientific or structural realists would agree it didn't change reality - because reality already had it, whether we knew it or not.

Well, I was thinking more along the lines of, say, multiplication and division - you can handle every single equation humanity has ever come up with without either of them. It might be messy and awful and annoying, but I would say in particular these operations are invented more than discovered.

So, more properly phrased, we created some operations.

I don't know what you're even trying to argue here.

We're not comparing math to reality (though there's a strong argument to be made that reality has a structure that is mathematical in nature - structural realism didn't die a scientific philosophy just because someone came up with a pithy saying), we're talking about if math is discovered or invented.

Most mathematicians would argue both - math is a language, we have created operations, axioms are proposed based on human creativity, etc., but the actual laws, patterns, etc. are discovered. Pi is going to be pi no matter if you're a human or someone else - we might represent it differently with some other number system or whatever, but that's a matter of representation, not mathematical truth.

So basically you're asking everyone to just trust you, a random commentator that provides no evidence or sourcing, over an article written with extensive sourcing, details, and explanations?

You might be the correct person here, but you're not going to convince anyone like this.

Most of the companies behind Valkey were writing significant code for Redis. It was certainly not a case of them paying nothing.

Valkey has some of the (formerly) most prolific Redis contributors for the era in which it was forked.

Avoidant behavior is defined as specifically attempted to avoid being exposed to things that remind you of your trauma.

Avoidant behavior is basically universally agreed to be a maladaptive behavior to ptsd.

Facilitating negative behaviors that prevent/increase the difficulty of overcoming trauma is not being kind to someone.

There has been no proper research on the effectiveness of "being given a trigger warning, and then not consuming the content because of it."

Well, there has been. From multiple angles. One, avoiding content because it might trigger you is just... avoidant behavior. Which is pretty much universally considered a bad thing. There's a big difference from seeking out exposure because you want to do your own exposure therapy (bad thing) and just letting yourself be exposed to things in a more organic fashion (good thing).

Two, most research indicates that TW do not actually reduce the consumption of content. Not all of the studies are on "did they help people process content they watched," as a lot of them are "did the TW make people not watch the content to begin with." Mostly it seems to haven no impact. A smaller subset of studies showed effects in other directions - both reduction and increase of content viewing after TW. If they reduce viewing I'd argue this is bad because it's avoidant behavior, and I suspect that the 'forbidden fruit' effect is also not positive because it's now giving you pre-viewing anxiety and is no longer the more organic 'let exposure happen naturally, don't just stop watching the news because it might contain stories about war.'

https://www.ptsd.va.gov/understand/what/avoidance.asp

A combat Veteran may stop watching the news or using social media because of stories or posts about war or current military events.

https://www.verywellmind.com/ptsd-and-emotional-avoidance-27...

The avoidance cluster of PTSD symptoms involves efforts to avoid distressing memories, thoughts, or feelings, and external reminders like discussions about the traumatic event or encounters with people or places associated with it.

I don't see how specifically avoiding content that contains triggers is anything but avoidance behavior as discussed above - avoiding the news or discussions about war is pretty explicitly facilitated by TW - before the clip plays on the news, by people posting it at the top of their social media content, etc. And media with the content would fall in line pretty explicitly as an "external reminder"

Like, I don't think someone who has been physically tortured and dealing with PTSD should watch Hostel or other torture porn, and I don't think a vet with PTSD should watch a compilation video of some of the worst horrors of war. So I'm not arguing for massive exposure or intentional forced exposure, etc. But the fundamental issue is that going out of your way to prevent yourself from being exposed to it at all, which is what TW facilitate if they were to work, is pretty definitionally avoidant behavior.

Generally agree with basically everything you wrote.

For me it's not even really political - I certainly am not aligned with the "heterodox" community that has been so actively against them. I think if people want to put trigger warnings on things, they should be able to make that choice, and people should be able to abide by them if they think they want to as well.

The issue is how it is framed as being important for helping people heal, like several people have spoken of it being important for in this thread. And I don't think the game/movie ratings ever really purported to be a part of that - indeed, it's always been more of an age appropriateness thing from my understanding.

If all of this was just "People should be able to make informed choices about the content they consume" and no one on any side was making claims about the mental health benefits for people with PTSD or similar, I think it would be a nonissue.

Basically, if you have anything like PTSD, you need an actual therapist not the collective hivemind of twitter (instagram these days?).

100%. Far far far more likely to get through it and overcome the trauma with a good professional guiding you through the process. Social media is just going to have you doing silly things like writing gr@pe or gr*pe as if somehow using a euphemism that you already map back to the original word is helping and it wasn't originally just trying to get around content filters.