Yet another Hacker News

GLM Built Its Own Inference Infrastructure

165 points whiteros_e 5 hours ago 129 comments

dada216 3 hours ago | parent

We built a complete production-grade inference service from scratch on a cluster of more than 100,000 Chinese-made AI accelerators. All production inference for GLM-5.3-Flash runs on this system.

freakynit 2 hours ago | parent

Most of the people had kinda guessed this when they decided to provide 100 trillion tokens for free.

gpugreg 1 hour ago | parent

It wasn't a secret either. They blogged about it last month: https://z.ai/blog/glm-5.3-flash#:~:text=Serving%20at%20Scale...

embedding-shape 3 hours ago | parent

I was gonna ask how people found their coding plans, and realized, have they massively ramped up the prices? Seems the middle plan is ~$80/month now, didn't that used to be like $20/month? Cheapest plan is ~$20/month currently.

They must have hit really hard scaling limits if the prices were hiked so much so quickly.

broodbucket 3 hours ago | parent

Yeah it went from a great deal to unviable compared to other providers imo. They really need to find a healthy middle ground

lompad 3 hours ago | parent

It just gives a taste of what we are all going to have to pay soon, once the model providers actually have to make money. And the era of "let's charge a dollar for every 10 dollars running the infra actually costs" is rapidly coming to an end.

And you can bet GLM is still ridiculously subsidized, just not as ridiculously as Anthropic and OpenAI.

chobbledotcom 3 hours ago | parent

This isn't true, you can pay for GLM 5.3 from a provider like Neuralwatt or Friendli who have no incentive to subsidize or loss-lead their inference APIs

jdiff 2 hours ago | parent

This introduces other incentives to cut corners and over-quantize.

breakingcups 1 hour ago | parent

They didn't pay for training

pyrophane 3 hours ago | parent

What provider are you using currently?

bbor 3 hours ago | parent

It's hard to know, since no one advertises the actual token limits (partially cause they're prolly complex / adaptive). So it seems much more likely that they just offer different pricing tiers than you're used to. Like, the $80 plan is still ~$80 of subscription quota, regardless of what else is offered.

For [API usage](https://openrouter.ai/z-ai/glm-5.3-flash#providers) they charge a bit more than the very cheapest providers of GLM-5.3-Flash, but not so much that a big price difference would make sense.

Daviey 3 hours ago | parent

I paid $360 annual for Max plan and currently averaging about 1BN tokens a day with their frontier GLM-5.3 model. This was clearly unsustainable for them and they've dropped this package.

disiplus 3 hours ago | parent

I also have a legacy pro plan and the only limitation is if you are trying to work in the morning from Europe because you are in the 3x usage overlapping China time but after 12 or so you basically can run it at least for me at least 3 parallel sessions all the time.

world2vec 2 hours ago | parent

1 billion tokens a day?!! I've done a lot of work these past 2 weeks with GLM-5.3. Like, a lot. And I've just passed 300 million tokens in total.

Can I ask where are you using all those tokens?

wartywhoa23 2 hours ago | parent

Something like this I guess: https://youtu.be/U-Rqv9dOB1U

p2detar 1 hour ago | parent

This is such a good video. Instant sub. Next to tech bros, we should also put AI-cringe bros.

tokai 2 hours ago | parent

300M for two weeks is surprisingly low. What are you doing that need so few tokens?

world2vec 2 hours ago | parent

It's not my main model (that would be Fable 5.1 Extra) but it's been doing agent-driven search and optimisation of a cross-trading ranking model (it's for work).

disiplus 2 hours ago | parent

I would suggest you to hook fable or 5.6 to check it regularly and its work because it gets lost easily on stuff it was not trained on. I'm doing some custom inference engine optimization and it's a workhorse but it can easily lose its way and if you don't recheck it you will get wrong answers in the end.

world2vec 1 hour ago | parent

Yeah that's what I already do. Fable writes the plan and checks things at certain milestones. Otherwise it does get lost indeed.

embedding-shape 46 minutes ago | parent

Kind of feels like this applies to every single model, from Astra to Qwen, they all eventually lose track of the plot unless you feed it some human's input that can steer them right every now and then. The only difference is how often you need to do so, and also how often you want to do so heavily influences how good quality the results will be.

_0ffh 2 hours ago | parent

Well, there's essentially two major ways to use these models: Pair programming or fully autonomous fire-and-forget code generation. The second strategy needs essentially zero input, so the number of tokens you can blow is practically only limited by API speed.

rubslopes 1 hour ago | parent

There's also a third way that can spend the most tokens: if the AI is used as part of the product, and not just a tool to build the product.

buckle8017 2 hours ago | parent

That's easy to do with many agents independently told to find bugs in a large codebase.

Daviey 1 hour ago | parent

I have 3-5 agent harnesses with large context windows working on different applications concurrently.

embedding-shape 47 minutes ago | parent

Share the resulting code from any one of those please? I've tried so many times to find a setup that facilitates parallel work + high quality results, but it's just impossible regardless of harness or model. Leave the agents alone for too long, and the entire thing just balloons out of control, and next you know you're sitting there with half a million LOC where 80% isn't even needed.

Daviey 25 minutes ago | parent

Most of them are not public, but a fun thing I did was a mario cli game - https://github.com/Daviey/mario/ (or `ssh mario.baby`).

I now exclusively use https://omp.sh/ as my harness:

I set it up so it never works in the main branch so subagents etc don't step on each others toes, and only merges back when complete: https://github.com/Daviey/mario/blob/main/.omp/hooks/pre/wor...

A good AGENTS.md is essential: https://github.com/Daviey/mario/blob/main/AGENTS.md

I then provide specifications for what I want, making sure it is unit tested.

asp_hornet 3 hours ago | parent

The way I look at it, their coding plan doesn’t retain data or use it for training making it one of the cheaper plans for me.

https://docs.z.ai/legal-agreement/privacy-policy

andy_ppp 3 hours ago | parent

You believe any of these companies care about the law? They care about winning and building the self improving AI as quickly as possible.

asp_hornet 3 hours ago | parent

I too am sceptical but I’ll take my chances. At least it’s helping the open weights.

criley2 2 hours ago | parent

I believe the that the companies who claim to not train on my data are more likely to not train on my data than the companies who refuse to even claim they won't.

Also why Meta gets a +1, just charge less money on the training path.

orf 2 hours ago | parent

I’m not sure that follows. You’re assuming that all those claims have the same weight, without considering the size, jurisdiction, reputation or even the general vibe of the company making that claim.

If you factor that in, then there are clearly different tiers: one you can trust, and one that may well just be saying that to increase market share with little reputational or legal consequences if they are found to be lying.

These are not equal.

asp_hornet 2 hours ago | parent

> I’m not sure that follows

To be fair, none of us are sure of anything and I think that’s the part that’s most irritating

orf 1 hour ago | parent

It’s more a polite way of saying “that’s crap”

asp_hornet 1 hour ago | parent

And mine a polite way to say “you are equally uninformed”. We’re not getting anywhere. All the best.

orf 1 hour ago | parent

FYI it’s helpful to actually say your point during a discussion. And if you don’t want a discussion then why did you comment?

andy_ppp 39 minutes ago | parent

Yes I sometimes think the "don't train on my data" is actually a good signal for "this data/person is probably better to train on because they want to keep something private". The whole copyright system should have stopped these guys from training on everyone's data and it did not, if you think they care about the privacy checkbox I think you're dreaming personally, based on their past behavior.

Havoc 2 hours ago | parent

>I was gonna ask how people found their coding plans

Very good - but I'm on a legacy plan. And coming up on a renewal that would put me on the watered down current plan. But with 50% legacy discount think it may be worthwhile. If I go to a competitor I'd be paying market rate.

>They must have hit really hard scaling limits if the prices were hiked so much so quickly.

Not really scaling - their plans were initially comically subsidized even more so than what the western providers are doing. More advert for an upstart than commercially priced.

probst 1 hour ago | parent

Way to restrictive in terms of tokens provided. I am on their largest plan, and quickly run into their limits. And that is using it selectively in addition to codex.

_aavaa_ 1 hour ago | parent

Their plans are still worth it if you use their models. You can see how many tokens you can except to get based on plan here: https://docs.z.ai/devpack/overview#estimated-token-allowance

The max plan will provide ~1,100 USD of GLM-5.3 or ~260 USD of GLM-5.3-flash per month for 168 USD. I can personally attest to these numbers through omp (~97% cache hit rate).

Unless you are able to highly parallelize (your work, you won't be able to hit your hourly or weekly quota using the flash model simply because it's so slow.

They give you ~3x more flash tokens, which maybe comes out to ~2x more actual work after accounting for the extra thinking it does to achieve the same result. The mental model, for not getting angry, is 5.3 is fast mode by default, and you can disable fast mode for 2x the work output at 1/3-1/10th the speed.

They're serving me 5.3 at ~40 tok/s and 5.3-flash at 30 tok/s (according to omp).

Schlagbohrer 1 hour ago | parent

That table assumes cache hit rate of 95% or better. Am I understanding this correctly that people really are doing such repetitive prompts (compared to each other, across the concurrent user base at that time) that only 5% or less need actually be computed by the intended LLM?

That is shocking. Is it per-token I wonder?

workbreak 53 minutes ago | parent

Every tool call is essentially entire prompt so far sent again with the response and that's why cache rates are so high for agentic workloads. This really bites when using expensive models since most models are 1/10 for cached input.

_aavaa_ 31 minutes ago | parent

If you are using their coding plan for coding, then yes you can easily hit such cache rates, with a good harness.

I’m getting 97%.

bbor 3 hours ago | parent

Well, other than the infrastructure they got from illegally routing millions of paying customers' requests through Anthropic's Opus 4.8 in a distillation attack...

jensb1 3 hours ago | parent

What is "illegal" about it?

bingud 3 hours ago | parent

breaking Anthropic TOS and misleading users

drbscl 2 hours ago | parent

Breaking TOS isn't illegal per se. It just allows for denial of services, and may define terms by which the provider can reclaim costs.

bbor 3 hours ago | parent

Are you joking...? Sorry if so! Just in case: It's illegal in both the PRC and the USA.

In the PRC, they[1] leaked tons of national secrets on the PRC's latest AI campaigns, the inner workings of their "opinion monitoring" (read: performative panopticon) and "stability" (read: violent oppression) departments, Chengdu's whole CCTV network, direct-energy weapons plans, espionage activities in Syria to hunt down Uyghur refugees, and god knows what else that Anthropic didn't divulge to us common folk.

In the US, it's very clearly an attempt to rip off a competitor. I'm not sure how else you could possibly see it. Even if you're a distillation fan in general (which A. why and B. plz don't), they did this through a network of Japanese and Signaporean shell accounts, presumably at least some of which were abusing Anthropic's subscription service in a ToS double-whammy, as it would be exorbitantly expensive otherwise. They also had to hack around Anthropic's API to get CoT traces, which seems impossible to explain away as anything innocent.

I've been beating the "China isn't necessarily an enemy, it's gonna take us all to handle AI" drum for literally years, but this attack was just... gross. Gross in scale and gross in arrogance. Not a good sign for the dawning alignment crisis, to say the least :(

TL;DR: Use these services if you want, but know that you're supporting aggressive escalations and companies that very clearly don't give a flying fuck about violating the law, much less your ToS. So... buyer beware, I guess.

[1]: For clarity, Z.ai was not alone in this, nor were they most egregious attack -- Moonshot.ai (kimi) took that coveted prize. DeepSeek was involved, too.

Bluestein 2 hours ago | parent

Nulla poena sine lege?

dgellow 2 hours ago | parent

What does any of this have to do with the legality of distilling Claude?

> use these services if you want, but know that you're supporting aggressive escalations and companies that very clearly don't give a flying fuck about violating the law, much less your ToS

From my European point of view the same risk/concerns apply when using US providers

jLaForest 2 hours ago | parent

Yes, wont somebody please think of the shareholders whose IP had been stolen...

podocarp 1 hour ago | parent

Source for 1? Are we sure those aren't hallucinations?

pjc50 1 hour ago | parent

> alignment crisis

Alignment is meaningless; as you've noticed, humans aren't all that "morally aligned".

If the tool needs safety measures it should be kept in a safe enclosure like we do with CNC machines, furnaces, and so on.

tuesdaynight 1 hour ago | parent

You didn't explain why it's illegal or why distillation is bad.

lelanthran 47 minutes ago | parent

Like Anthropic and OpenAI are? After all, didn't they distill all the information in the world into their model(s)?

I mean, if they get to distill other's IP, why can't others distill their IP?

woadwarrior01 2 hours ago | parent

That is such a canard, IMO. FWIW, Anthropic and OpenAI encrypt "thinking" token outputs in their models, while Chinese labs don't. If anything, it's more likely that everyone is using open-weight models in their synthetic training data generation pipelines. It's way easier to distill from logits than it is to distill from hard tokens.

https://x.com/EricSimons/status/2099252922098061714

phoghed 2 hours ago | parent

We weep for Dario, that he had to suffer such a devastating attack against his Terms of Service.

butterNaN 2 hours ago | parent

Eh, even if this was true, then they're merely stealing from thieves. Anthropic did break a ToS or two to get training data themselves.

pjc50 1 hour ago | parent

Anthropic infringed the copyright of basically every author on the planet: https://www.anthropiccopyrightsettlement.com/

No real reason to respect any terms they might want to impose. Besides, if you want to break TOS, just have an agent do it; "everyone" running these things agrees there's no corporate or moral liability for what your AI does.

_aavaa_ 1 hour ago | parent

I'm not defending their actions, but we should be clear about where the law currently stands: Anthropic was found to infringe because of the torrenting, not because of the training.

lelanthran 49 minutes ago | parent

I have very little sympathy for thieves who get robbed of the goods they have stolen.

HarHarVeryFunny 48 minutes ago | parent

If you understand what they have achieved here, then the notion that they are bottle-necked on training data is absurd.

I wonder how you imagine that China built their own space station? Reliant on using American made duct tape, perhaps?

Do you realize how reasoning models are being trained nowadays? You design/build simulation environments to run agents in, with the environment providing the RLVR "verification" scoring. So why won't Ziphu use GLM to build their own RL training environments? Do you think they are not doing this?

rob74 3 hours ago | parent

This article left me with one immediate question: "WTF is GLM?".

Honestly, I have no idea what z.ai is either (I'm aware of an AI-enabled editor called Zed, but that's under zed.dev), so it's a bit presumptuous from them to assume that everyone is familiar with their product...

fxwin 2 hours ago | parent

It's presumptuous for them to assume that a reader of their blog is familiar with their product?

Also I feel like the obvious way to read the very first sentence is that GLM is a language model

> As we develop GLM, the model sometimes exhibits capabilities that surprise us

jbonatakis 2 hours ago | parent

z.ai is a fairly well known AI lab out of China and their GLM models are probably the most popular outside of Anthropic or OpenAI’s. I don’t think it’s presumptuous for them to not introduce themselves in a post on their own blog, I think you’re just a bit out of the loop here.

drbscl 2 hours ago | parent

>As we develop GLM, the model sometimes exhibits capabilities that surprise us, and even unsettle us.

Come on now

Also, why would they introduce themselves on their own blog?

Mashimo 2 hours ago | parent

A ai model family similar to Codex, Gemini or Claude.

Where GLM-5.3-Flash is the newest "small / fast" model.

peri-cl 2 hours ago | parent

It's only the top open-weights LLM in the world,

https://artificialanalysis.ai/#intelligence-category-tabs

bogdan 2 hours ago | parent

I don't get the outrage. Do you post this kind of stuff on every topic on hackernews that you are not knowledgeable about?

rob74 1 hour ago | parent

Maybe my post sounded harsher than I intended, and yeah, it's probably on me that I'm not familiar with GLM. Actually the other major Chinese LLM Kimi does ring a bell, maybe it's because three-letter acronyms are a dime a dozen and annoy me because I'm confronted with them regularly at work too (people at my company seem to love acronyms), but that's obviously on me too...

tokai 1 hour ago | parent

It didn't read as harsh. Only unaware and you broadcasted that you don't have the decency to do basic searches.

bogdan 20 minutes ago | parent

> Maybe my post sounded harsher than I intended

Appreciate the clarification. For me it was the "F" in "WTF" that tipped me. Other than that, it's more than fair for you to not know what GLM is. Things are moving so fast that I would be surprised if anyone can keep track of it all. Cheers, have a grand day!

HarHarVeryFunny 1 hour ago | parent

Ziphu, aka Z.ai, is the company that makes GLM (a very competitive Chinese LLM).

Why would you be reading their corporate blog posts if you don't even know who they are?!

Argonautlabs 2 hours ago | parent

Different angle on the same model: the full GLM-5.3 (744B MoE, 4-bit experts, 434 GB on disk) runs on a single MacBook Pro M5 Max with 128 GB by streaming the experts from NVMe SSDs instead of keeping them in memory.

One drive gives about 2 tok/s; striped across four drives it reaches 3.5 tok/s with byte-identical output, and our best internal build with a not-yet-published patch does 4.2.

Method and numbers: https://github.com/argonautlabsai/argodrive (built on antirez/ds4).

tipsytoad 2 hours ago | parent

seems unusably slow, and is this for short context?

Havoc 2 hours ago | parent

Interesting that the tone of announcements between US and Chinese providers is converging.

GLM has in the past been more technical rather than speculation about future development on RSI etc.

Also curious whether those 100k accelerators are entirely locally made. If that's genuinely end to end on all components including lithography, memory, design etc then that is quite a feat.

dude250711 2 hours ago | parent

Any details on the latest approach to distillation would also be very interesting.

Schlagbohrer 1 hour ago | parent

I am surprised at the lack of open-weights models in the >35B, but <200B range. I keep thinking about devices like the NVIDIA Spark and AMD Ryzen Halo, which have their 128GB of combined memory, but there are so few models made for that range. Nearly all the open weights distillations are for larger customer bases with <24GB VRAM.

MaKey 4 minutes ago | parent

The market is too small.

bitexploder 2 minutes ago | parent

Qwen Flash Next 3.8 … even at 3 bit quant it is very solid.

HarHarVeryFunny 1 hour ago | parent

Ziphu (who make GLM) use Huawei Ascend processors made by SMIC. Huawei use a combination of domestic memory from CXMT and leftover (pre-sanctions) memory from Samsung.

Just like the rest of the world, including the US (Intel, Micron), SMIC are currently using ASML lithography equipment (DUV, not EUV), but Shanghai Aishengna are now moving into early production with their own DUV machines, with SMIC and CXMT as early customers.

There is also a state sponsored Chinese EUV development underway.

jonstewart 2 hours ago | parent

Necessity is the mother of invention. The shortsighted protections put on chips, etc., by the US has forced Chinese AI industry to adapt or die. Guess what their response to this fitness function has been? Kudos to Z.ai on their inventions and excellent write-up, which reads like humans wrote it.

HarHarVeryFunny 1 hour ago | parent

Wouldn't it be refreshing if OpenAI and Anthropic were this open, and spelled out how they were using their own models during development and rollout?!

All I can recall reading from OpenAI about what they have actually done in the name of "RSI" is using one of their models to help automate the training process.

zicohacks 1 hour ago | parent

US chip export restrictions may actually be an advantage for China's AI Infrastructure. Chinese companies are forced to speed up developing their own AI chips

HarHarVeryFunny 1 hour ago | parent

China themselves recognize this. After Trump relaxed sanctions and allowed NVIDIA H200 sales to China on a case by case basis, the Chinese government stepped in to essentially block it!

In addition to Huawei who make the Ascend series that Ziphu are using, there are also at least a half dozen or so other Chinese companies also making their own AI accelerators.

0xbadcafebee 58 minutes ago | parent

And this wouldn't have happened if we had tried to get them to buy our hardware rather than trying to gatekeep. Protectionism never works in the long term.

ipsod 27 minutes ago | parent

Look at how China does it. They'll happily sell us everything we want - more than enough of it, cheap enough, to put all of our own manufacturers out of business.

Seems to work for them.

freakynit 25 minutes ago | parent

US companies should now be more worried about Chinese companies flooding the market with their, hopefully, very affordable GPU's. The scale at which they can manufacture stuff is unmatched anywhere else. Nvidia can kiss goodbye to their 75%+ profit margins.

Almost everyone knew that these sanctions would backfire within a few years. You can't really put sanctions that have noticeable negative effects on bigger economies. They only work for small to medium economies. I believe sanctions on any economy in top 10 would fail.

HarHarVeryFunny 18 minutes ago | parent

Same thing with Trump not helping Ukraine and berating NATO. He thought he held all the cards, but now Ukraine has a thriving battle-tested drone industry, UK and France have stepped in to replace the US with advanced missiles and anti-missile systems, stepping up their own production and transferring IP to Ukraine.

Now, the US is left out in the cold with little influence left, themselves now the ones with an anti-missile shortage.

menaerus 58 minutes ago | parent

It was evident that this will happen.

> Compared with our initial baseline on the same hardware, we achieved a 3× improvement in end-to-end serving performance, reaching hardware efficiency and per-token cost comparable to mainstream NVIDIA GPUs. This demonstrates that Chinese chips can support frontier-model inference efficiently and economically at scale.

stogot 48 minutes ago | parent

It created demand that would not have been there without restrictions

chung8123 1 hour ago | parent

I might be missing something but when I went to their site they are more expensive than Claude. Why would I pick GLM over Claude? Is it they just offer more tokens in their plans?

tokai 1 hour ago | parent

For one you would have to use Claude if you pick it. But seriously there is no way for you to determine if one is a better offer than the other, when the usage/tokens/credits are vague, detached, and won't tell you much without trying both.

gpugreg 55 minutes ago | parent

    > Why would I pick GLM over Claude?

To support the company that makes their model weights available for download, while Anthropic lobbies to restrict access.

Bawoosette 52 minutes ago | parent

What are you referring to? Given the audience, my instinct is to assume "plan" refers to the GLM Coding Plans, which are all cheaper than their Anthropic counterparts. As far as I can tell, the API costs are also all cheaper than their roughly equivalently capable Anthropic models.

menaerus 28 minutes ago | parent

Anthropic: 17 USD (pro), 100 USD (max)

GLM: 80 USD (pro), 168 USD (max) -> with "limited-time event" discount this becomes 56 USD and 117.6 USD

I also don't understand why are they so much costlier, and I would also like to give it a try.

ipsod 18 minutes ago | parent

> Anthropic: 17 USD (pro), 100 USD (max) GLM: 80 USD (pro), 168 USD (max) -> with "limited-time event" discount this is 56 USD and 117.6 USD

GLM's "Max" plan is (was?) equivalent to 3x Claude's 20x ($200) plan.

throwa356262 1 hour ago | parent

    "We implemented a series of aggressive memory optimizations, including..."

This whole thing sounds like industrial scale auto-research, but done by people who actually know what they are doing.

0xbadcafebee 59 minutes ago | parent

This is a really funny sounding post. They sound like they just found out that increasing your automation gives you increased capabilities at faster speeds. They also sound like they just realized AI makes hard things easier.

But what really kills me is the idea that these companies are using Python for production inference. I mean really? Have you seen how bloated and slow Python is? Do global locks really sound like a strategy for fast dynamic computation?

wolttam 38 minutes ago | parent

Python acts as an orchestrator of accelerator libraries and does none of the inference math directly

esseph 28 minutes ago | parent

> Have you seen how bloated and slow Python is?

Yes, but it's calling C code.

kamranjon 8 minutes ago | parent

Someone tell this man about vLLM!

HarHarVeryFunny 8 minutes ago | parent

It's not that they "just found out" - what they are saying is that while they were previously dogfooding because it's good practice, now that their models are so much stronger they are using them because it helps accelerate.

If you look at how many years the whole NVIDIA and CUDA ecosystem has been evolving, it's certainly impressive how they've just stood up and optimized this CUDA-free 100,000 node cluster in just a few months.

KronisLV 54 minutes ago | parent

Time to tackle consumer GPUs next, since I’m not getting that Intel Arc B770.

konart 52 minutes ago | parent

If only this infrastructure could handle all the traffic. I've tried using glm via z.ai - and it's a snail kind of slow.

And at the same time you have pretty strict limits to your usage, so in many cases you can't even let it work all night, as you will reach your limit faster than that.

9cb14c1ec0 31 minutes ago | parent

Given the huge amount of money being spent on AI chips in the US, what prevents US AI labs from doing the same level of software optimization? It could be a solve for some of the capacity constraints.

a012 25 minutes ago | parent

> what prevents US AI labs from doing the same level of software optimization?

Because they don’t have to. Most of the time money would buy you newest and/or more hardwares so there’s low/minimal interest to optimize the code or approach.

vblanco 20 minutes ago | parent

They have already been doing it for months https://openai.com/index/openai-broadcom-jalapeno-inference-... . OpenAI on their custom chip brought up lightspeed deepseek as experiment by using AI in the exact same way as this zAI blogpost. And the kernel optimization contests/etc have all been havily done through AI based optimization loops for half a year+.

esafak 12 minutes ago | parent

I'm not feeling any of this speed optimization; it's dog slow.

Signed, a customer.