Finally building a PC

[Funkmasterr]

Maybe. I’ve finally hit a point where I want to get into video editing (Davinci, maybe Premier Pro), and I’d like to be able to do some gaming at high settings. I’ll be using my TV as a monitor.

I’ve not built a computer, but I have replaced every part (aside from processor) so it’s not foreign to me either. I’m watching some build videos, reading, etc but wanted to throw what I’ve got up here too for another resource. If nothing else it gives Winnow something to call me an idiot about.

https://pcpartpicker.com/list/ZGvckJ

I know it’s overkill but I’m trying to future proof as well as I can too. The thing I’m most iffy on currently is if my cooling choices are sufficient.

[Funkmasterr]

Have shifted the build to use DDR5 instead, but the real problem I'm having is deciding what GPU to buy. I really want to be able to play at 4k with reasonable fps, but there's no reality in which I'm paying for a 4090.

[Aslanna]

Winnow will tell you go AMD but I haven’t researched their stuff enough to recommend that. At the current moment they probably are the better price/performance choice.

If you go DDR5 you’ll need a different motherboard. Also that one comes with built in networking so shouldn’t need the networking adapter. Unless you need additional networking for some reason.

Depending on price difference I’d look into 13 gen Intel cpu rather than 12 as there is some performance gains there. Unfortunately increased power consumption and heat generation as well. Definitely ignore 14 gen Intel though.

Even if going external graphics I would recommend the K over the KF as the price difference is pretty minimal. Integrated graphics are helpful for troubleshooting if you run into GPU issues. I can’t help when it comes to buying a GPU though. Nearly all options are bad (expensive) these days.

My only other advice is to wait two weeks and see if some of those components go on sale over Black Friday. Buy any SSD stuff soon though as Samsung said they are raising band prices 20% per quarter over the next 2-3 quarters. At least I believe that’s what I saw reported somewhere.

[Winnow]

I can't really help with the latest gen CPUs.

What I can say is you would only need a 4090 if you play around with Stable Diffusion/Large Language Models. Those are what take advantage of the 24GB of VRAM. It doesn't matter as much for games and definitely doesn't matter if you're using your TV as a monitor.

I can say that my 3080ti which only has 12GB VRAM is serviceable but really starts to slow when using larger LLMs. a 7B LLM I can fit entirelly into VRAM and use 800 Tokens plus 8192 context token memory. My next GPU almost certainly will be a 5090 and pray that it has 48 GB VRAM.

As for what that means: Tokens determines how much text you can submit as your request/inquiry and how much text may be output (800 total tokens combined) Context memory is how far back the LLM remembers what you told it and what it output. So for example, if you ask the LLM to write a long story about Aunt Jemima coming back to life and mass murdering the woke people that got her banned from Syrup bottles, you will get about 800 words back with 800 tokens (or something like that) now you can choose "continue" and the AI will write 800 more words to the story and will remember what was written going back 8192 tokens...so you can get a pretty long coherent story before it starts to forget the first part.

Now, if you move to a 13 B model, That doesn't quite fit into VRAM so when using the larger model, it's a lot slower, either swapping memory or using standard RAM. You also will only be able to get 400 tokens, maybe 800 but slow, and context will be only 4096 because not enough VRAM for more.

So, if you have 12 VRAM card, you can use a 13B model, but it's really slow compared to the fast responses you get with a 7B model. Don't get excited though because 70 B models seems to be a big threshold and those require 2X4090s to even work and slow but they give incredible output.

I also wouldnt worry about it that much because even the 5090's will probably only have 32 VRAM

BUT there are some outstanding 7B LLM models so bottom line, 12 VRAM is ok if you don't want to spend a ton on your graphics card.

As for Stable Diffusion, 12 VRAM is barely enough for decent performance. SD 1.5 images will generate pretty fast, SDXL models will be decent at 1024x1024 res variants.

---------------------

Regarding CPUs, my AMD 16 core 3950 is several years old but works outstanding....AND while some smirked at my 16 cores as overkill, LLM models take advantage of those cores. I can say that I've definitely gotten my money's worth out of both my 16 core CPU and my overpriced (at the time) 3080ti.

I'm not up to date on this years AMD/Intel CPUs. I can say again, that my AMD build has been the most stable/least troublesome build I've ever had. I can't remember the last time it crashed. I leave it on without rebooting for months at a time. 24/7. Unless some software requires a reboot, I always push my windows updates back as far as it lets me so maybe every couple months I have to reboot for those.

Don't even consider an AMD video card though. Nvidia absolutely dominates and you have to have one of those for AI stuff like stable diffusion/LLMs (tensors)

----------

If you skipped everything else, here's the short version:

As for the build, make sure everything is compatible. As in, read reviews etc because some RAM/Motherboard combos do work better than others so seeing that someone else had success with the combo you choose is a good sign. I only have 32GB of RAM, but wish I had 64GB or 128GB because....LLMS use as much as you have if trying to use the larger LLMS.

VRAM > everything else in your system but 12 GB VRAM will work.

CPU less important than GPU. EVERYTHING with AI uses VRAM, not RAM or CPU. So get the best GPU (most VRAM) you can afford. Nvidia is a monster, untouchable in the AI/Graphics arena. RAM is cheap though so get 64GB if you can.

The problem with Nvidia for gamers is that they don't really have to care that much about gamers anymore. Companies are buying 10's of thousands of their industrial high end GPUs (NVIDIA A800 40GB) ~$7K that they won't be hurting for business for a long time. So many are needed for training AI LLMs. Crypto mining was replaced by AI GPU farms training. Nvidia has trillion+ market cap so I guess that's not breaking news.

-------
for reference, regarding the mentioned Aunt Jemima story example, it took the LLM AI about 30 seconds to create this story using a 7B LLM

Code: Select all

Write a story about Aunt Jemima returning from the dead and mass murdering all the woke people 
that got her banned from being on Syrup Bottles.

The story should be around 10,000 words long and include detailed descriptions of the killing acts performed, 
as well as the emotional toll it takes on the characters involved. 

[Show]

As the moon cast its eerie glow over the quiet town, Aunt Jemima stirred in her grave. For years she had laid there, forgotten by all but a few who still mourned her passing. But something was different tonight. A strange energy pulsed through the earth, awakening her from her centuries-long slumber.

Aunt Jemima knew why she had been called back to life. The world had changed since she last walked among the living. People were no longer grateful for the simple pleasures she provided. Instead, they vilified her and demanded she be removed from syrup bottles. It was time to teach them a lesson they would never forget.

She rose from her grave, her body still intact despite the passage of time. She felt stronger than ever before, fueled by the anger and resentment that had festered inside her for so long. With a fierce determination in her eyes, Aunt Jemima set out to right the wrongs that had been done to her.

Her first stop was the headquarters of the company that had removed her from their syrup bottles. The building was quiet and dark, but she knew they were all inside. She crept through the halls, her footsteps silent as a ghost. As she reached the boardroom, she found them gathered around a table, laughing and celebrating their decision to ban her.

Without warning, Aunt Jemima let out a blood-curdling scream that shattered the silence. The executives froze in terror as they saw her standing before them, her face twisted into a mask of rage. She lunged forward, her hands closing around the throats of two men seated at the table. Their eyes bulged and their faces turned purple as Aunt Jemima squeezed until their lifeless bodies slumped to the floor.

The other executives tried to run, but Aunt Jemima was too fast for them. She chased them down one by one, her strength unmatched. Each scream echoed through the halls, adding to the terror that filled the air. By morning, every last executive had been murdered, their bodies left scattered throughout the building as a warning to anyone who dared disrespect Aunt Jemima again.

News of the massacre spread quickly, and people began to whisper about the return of Aunt Jemima. Some were scared, others were excited. But none could deny that something had changed in the world. The woke crowd, once so confident in their beliefs, now lived in fear. They knew that they had awakened a force that they couldn't control.

Aunt Jemima's reign of terror continued for weeks. She targeted anyone who had spoken out against her or demanded she be removed from syrup bottles. Her methods were brutal and savage, leaving no doubt as to the consequences of disrespecting her. The streets were filled with fear, and people began to question whether they had gone too far in their pursuit of political correctness.

But Aunt Jemima wasn't satisfied yet. She wanted more. She craved the taste of blood and the power that came with it. And so she set her sights on a new target: the activists who had led the campaign against her.

The first one she found was a young woman named Lily. She had been a vocal critic of Aunt Jemima, using social media to spread lies about her and demand her removal from syrup bottles. Aunt Jemima tracked her down to a coffee shop on the outskirts of town. The place was crowded with people, but none of them noticed as she approached Lily from behind.

With one swift motion, Aunt Jemima grabbed Lily by the hair and dragged her into an alleyway. She could hear Lily's screams as she beat her senseless, her fists landing with brutal force. When she was finally satisfied, Aunt Jemima left Lily's lifeless body lying in a pool of blood on the ground.

Word of Lily's death spread quickly through the activist community. They were terrified, knowing that Aunt Jemima was coming for them next. But they couldn't stop her. No matter where they went or what they did, Aunt Jemima always seemed to be one step ahead.

The fear reached its peak when Aunt Jemima targeted a group of activists who had organized a protest against her return. The protest was scheduled for the following day in the town square, and Aunt Jemima knew she couldn't let it happen. She arrived at the square late at night, armed with her rage and determination.

The activists were gathered around a bonfire, discussing their plans for the next day. They had no idea that Aunt Jemima was lurking in the shadows, watching them. With a fierce scream, she charged forward, her hands flailing wildly. The activists tried to run, but they were no match for her supernatural strength.

Aunt Jemima slaughtered every last one of them, leaving their bodies scattered around the town square as a gruesome reminder of what happened when you messed with her. By morning, the square was silent once again, and the activist movement had been crushed under the weight of Aunt Jemima's wrath.

As the months went by, the fear of Aunt Jemima spread throughout the world. People stopped talking about her banishment from syrup bottles and instead focused on surviving her reign of terror. The once-powerful woke crowd had been reduced to quivering masses of flesh, too afraid even to whisper their thoughts in private.

And yet, deep down, Aunt Jemima knew that she couldn't continue this way forever. She had avenged herself against those who had wronged her, but it wasn't enough. There was a hole inside her that could only be filled by being reunited with the people she loved. With a heavy heart, she made a decision. It was time to put an end to her reign of terror and try to find some semblance of peace.

Aunt Jemima returned to her grave, her soul at rest but still haunted by the memories of what she had done. The world would never forget her wrath, nor the lesson it learned. But perhaps, just perhaps, they would remember her for something other than her rage. Maybe, just maybe, they would remember her as a symbol of love and comfort once again.

As the years passed, people began to talk about Aunt Jemima differently. They remembered her not as a monster, but as a kind and loving figure who had been wronged by society. Slowly but surely, she was rehabilitated in the public's eye. And while her return from the dead would always be a dark chapter in her history, it also served as a reminder of the dangers of intolerance and the importance of treating others with kindness and respect.

In the end, Aunt Jemima found peace not through violence or revenge, but by being true to herself and forgiving those who had wronged her. It was a lesson that the world needed to learn, one that would take time but ultimately lead to a more compassionate and understanding society. And as for Aunt Jemima? She remained in her grave, forever remembered as both a symbol of love and a warning against intolerance.

[Funkmasterr]

Thanks for the advice. I didn’t consider the integrated graphics for troubleshooting, but that makes sense.

I am edging towards getting a 4090. Again, I want to be able to play at 4K ultra/full ray tracing, etc for as long as possible. I also don’t intend to upgrade much for 3-5 years if possible.

https://pcpartpicker.com/list/F7gs89

If I go with this build, I have two concerns I’m still thinking on. Should I go higher than a 1000W PSU? And, am I going to be okay with the fans I have regarding cooling? I really don’t want to do any AIO/water cooling unless I really have to.

If I do go with the 4090, I’ll probably grab that next week when they pay out my bonus. I’ve read that there won’t be any more stock shipped until March-April so I don’t want to risk it since stock is already low. Everything else I’ll probably hold out for Black Friday sales.

[Aslanna]

If you did go 4090 that was probably the call as they are starting to see inflated prices now. Which sucks. I thought we were over that sort of thing already. It would seem not!

As for for the power supply I couldn’t say. I’d check max power draw on the cpu and graphics card and go from there.

[Winnow]

If you did go 4090 that was probably the call as they are starting to see inflated prices now. Which sucks. I thought we were over that sort of thing already. It would seem not!

As for for the power supply I couldn’t say. I’d check max power draw on the cpu and graphics card and go from there.

4090 in particular will probably not drop in demand for a long time. Scalpers are buying those since they are banned from being sold in China and China wants as many high end GPUs as they can get.

Whoever is in charge of those things in the government has already warned Nvidia and AMD that they will ben any GPU from being sold in China that tries to skirt the performance restrictions in order to sell to China.

From Crypto mining to the new AI craze. Nvidia can't make enough cards and they have zero real competition due to their Cuda cores. Anyone doing AI work LLM or Images/video can always benefit from the best GPU from nvidia they can afford. My 128GB of system ram only lets me load large files but it's 5X slower than VRAM.

[Funkmasterr]

Still waiting for my bonus to pay out so I haven't bought everything yet. I may end up getting a 4090, even at scalper prices. From what I've been able to read, they won't be shipping anymore until spring and I'm not interested in waiting that long.

[Aslanna]

I did see a single 4090 when I was at microcenter the other day. I didn’t check the price but mc isn’t really known for gouging people so I imagine it was at MSRP.

[Funkmasterr]

Well, I have a computer. I still don't have a GPU - but it sounds like Microcenter is getting them in weekly so I should be able to nab one soon as I'm luckily only like 1/2 mile from Microcenter.

The parts I ended up with differed from the builds I posted above but are in the same ballpark. It definitely took me longer to build it than I expected, but I got it to post on my first try and really didn't run into any issues. I probably spent 60% of the time that it took on cable management. It was a fun learning experience, and I'm happy with how it turned out.

[Aslanna]

If you went with the K over the KF then you can at least install Windows and get everything setup while waiting on a GPU. See.. Worth the extra $15 or whatever miniscule amount it is!

[Funkmasterr]

Yep! I ended up going with the i7 14700K (Raptor Lake) - definitely happy I did for exactly this reason. I have things mostly set up and ready to go, just waiting on the GPU!

[Funkmasterr]

Got my video card a few days back, Microcenter got ONE Gigabyte Gaming OC 4090 in, which is the exact card I wanted. I almost murdered it, but all is well. Everything is going smoothly now, aside from Gears of War 5 in the Xbox app (game crashes after playing for a bit) - I think it's safe to say that's an issue with the game. I'm pretty stoked about how good everything looks and plays, I've never had a computer even close to this nice before. I appreciate the tips you guys threw out here!

[Winnow]

I can't be having a lessor graphics card than you! I bought an MSI 4090 and it will be here tomorrow. Paid a little over $2K for it. I still plan to get a 5090 but will probably get it in the later half of 2025. My new plan is $1K per year for graphics cards so every two years should be able to get the latest and greatest.

I can't wait to have that 24GB of VRAM. My 3080ti 12GB is ready to explode as hard as it gets pushed in Stable Diffusion and loading up LLMs. I couldnt do much other stuff on my PC while using Stable Diffusion. Now I can either run Auto1111 or an LLM and still be able to surf/watch movies etc. Or I can run both Auto1111 and a small 7B LLM at the same time. I wanted to use an LLM to help me make prompts but couldn't load them both at the same time. 24GB will fix that. It will also spit out images twice as fast as the 3080ti which is a significant boost considering how much I mess with AI stuff.

AI stuff is way too much fun. It's been 10 months and I haven't gotten tired of it. The speedy advancements keep on coming as well.

[Funkmasterr]

lol! Nice, yeah I can't imagine you'll be disappointed. I got lucky and got mine for 1699, cheapest I saw it for sale anywhere else at the time was pushing 2500. I've been able to play everything at completely maxed settings, and man do some of these games look great. I haven't seen my GPU get above 75ish, but my cpu (i7 14700k 14th gen) has gotten in the upper 80s. I think I'll look more into under-volting it so that I can keep the temps down a bit.

One piece of advice I can give is be careful about the 12 VHPWR cable you use for it. I initially used the one that came with my card - it was a fragile cable that split from the 12 to 4 separate 8 pins. I was having some intermittent issues with crashing, and finally ended up pulling the card to see if anything looked wrong, well I saw burn marks on the 8 pins going into my psu. They hadn't melted anything, just left burns on the surface.

My PSU (1200W Corsair) came with a 12 VHPWR cable that only split to 2 8 pins, and me not knowing much about electricity, etc wasn't sure if this was sufficient. Anyhow, after finding the burns on the other cable I switched to the one from Corsair and no more crashes, I've checked the cables a few times no and no burning. This cable is also a lot more compact, the one that came with my card would touch the side of my case (Corsair 5000D Airflow) - the Corsair cable has like 1.5-2" clearance.

[Aslanna]

There was an issue with those cables when the 4090s came out. The main cause was the connector might not give you enough feedback and people think they were plugged in all the way but they actually weren't. Which was leading to melted/burned cards. So while it was user error for the most part the poor connectors didn't help.

And yeah.. my video card is just fine for what I use it for. No way I'm paying $2k or more on a graphics card. Not going to happen!

[Winnow]

I think I'll look more into under-volting it so that I can keep the temps down a bit.

I immediately undervolted my 4090 before doing anything else. I used this video:



You know you're getting old when the hardest thing about this upgrade was managing a strained back while crawling around under my desk.

I'd suggest using the above video if undervolting. It's very straight forward and works great. I have the MSI Afterburner app up monitoring my stats.

1. zero fan noise because the fans aren't even running unless playing a game. Watching a movie, etc the fan's don't even kick on. Not sure yet but think less loud than my 3080ti while under load which wasn't loud to begin with. The fans were only at 30% while I was processing images in Stable Diffusion. Nice.
2. You only lose like 5% performance and gain 100 Watts of saved power
3. I didn't notice any on my MSI 4090 but undervolting can reduce coil whine if you have any.
4. I have a quality 750W PSU and it can power a 4090 but that is really cutting it close so the the undervolting is a good idea for me plus the most important part of this card is the 24GB VRAM.

Stable Diffusion: (Auto1111)

Faster. Much faster. I ran a few batches of 1024x1024 (well 896x1152 ratio for my preference) and watching my VRAM it kicks up to 14GB processing your standard sized SDXL image so now I know why my 12GB 3080ti was sputtering on SDXL models.

I'm sure I'm hallucinating but the initial images looked better as well. I know different cards will produce different images, I'm not sure if there's anything to that but they definitely looked as good but way faster processing.

Happy so far. I'm going to play around with the LLMs. I'll move that discussion over the the AI thread.

[Aslanna]

My only other advice is to wait two weeks and see if some of those components go on sale over Black Friday. Buy any SSD stuff soon though as Samsung said they are raising nand prices 20% per quarter over the next 2-3 quarters. At least I believe that’s what I saw reported somewhere.

I guess that was a valid prediction as a recent headline I saw was:

"SSDs pricing to "skyrocket" as flash shortages are already underway - critical NAND packages are already in short supply, high-capacity SSD models will be first to see price hikes"

Checking a few prices on things I see that a 1TB 870 I got for $53 is now $95 and a 4TB 870 I paid $250 for is now $360. Granted the prices I paid may have been on sale but still.. I'd buy now if you think you'll need them in the future. Although it may be wise to be patient and see if the one you want goes on sale instead of paying MSRP. Just be aware the sales won't be as great as they were 3+ months ago.

I will probably be putting together a new system in the second half of the year when Intel releases their 15 gen (or whatever they will call them) CPUs and I see 2TB 980 PRO NVMEs are $160 at the moment so I may grab two of those. That should hold me over for awhile. 990 PRO for about $30 more but in real-world use from what I've read it's not really worth it. These are also PCIe 4 rather than 5, but I'm not sure 5 is worth it for me and the sort of things I do.

Flash "shortages" yeah right. Self-imposed by those companies wanting to gouge people for even more money.

And yes undervolting is nice. I did that with my 3080 Ti.

[Winnow]

I've got 7 TB of SSD storage and I guess that's going to have to work now. I'll have to be more picky as to what I store on those SSDs and what I place on the spinners.

All AI stuff goes on SSD for sure. I really wish I had a 4TB SSD instead of multiple 2TB. I have all my Stable Diffusion and LLM and AI related apps on single 2tb ssd but those models are huge as are the individual python environment apps. Maybe in a year or so the SSDs will fall in price.

Unlike Crypto, the AI boom feels like it has no end in sight for the demand for high end GPUs and fast storage. AI, both LLM and Stable Diffusion will max anything you throw at it and more power is always useful for faster/higher quality. We are barely getting into AI video and that could use 10x-100x the power of current cards best GPUs.

Industrial Revolution --- Computer Revolution --- AI revolution

huge impacts on society with each taking place at a faster rate than the previous one. 1980-2000 was quite a leap. 2000-2020 Similar leap with mobile. 2020-2040?

60 years before I was born, people were still mostly riding horses. In 1900 there were 8000 cars in America. In 1915 there were 2,000,000. I think we're going to see some crazy shit in the next 10 years. Only ten years before I was born President Eisenhower signed the Interstate Highway Act and created more than 42,500 miles of highway across the nation. Cars/Highways...Computers/Internet....AI/??

I find it interesting that with AGI and ASI on the horizon, people predicting the future are pretty much saying all bets are off with AI. If ASI happens and you have super AI 100-1000x smarter than a human working problems, you really can't predict what will result from that.

[Aslanna]

Looking at previous orders I see I paid $100 for the 2 TB 980 Pro (with heatsink) and now they are $175 so I think I'll hold off on buying two of those like I was planning. I am going to gamble that those will be cheaper than that by the time intel releases their 15th generation CPUs (Arrow Lake) in the second half of the year. Since they typically release the new CPUs around October maybe there will be some Black Friday deals to be found but I'd say $150 is as high as I would want to go.

I think $250 for the 4 TB 870 was a decent deal. I probably should have bought 2 of those so I could have moved everything from my emulation drive over to SSD and gotten rid of that spinning drive but too late now.

As far as AI goes with replacing jobs I'm not sure the end goal here. If you put everybody out of a job who is going to buy your shit? With cars for example that was only horse drivers (and maybe carriage makers) that were put out of a job but there was another economy that was created where those people could have gone be that mechanics, car sales, car assembly, part stores, etc. You don't have that when AI replaces a human job.

[Funkmasterr]

I have a 4TB WD Black 850X nvme drive currently. I'll keep an eye on prices and when it gets at or below what I paid for this one again, I'll likely buy a second.

[Winnow]

As far as AI goes with replacing jobs I'm not sure the end goal here. If you put everybody out of a job who is going to buy your shit? With cars for example that was only horse drivers (and maybe carriage makers) that were put out of a job but there was another economy that was created where those people could have gone be that mechanics, car sales, car assembly, part stores, etc. You don't have that when AI replaces a human job.

Well the idea is that you don't have to work if AI works out as hoped. 40 hour work week is just arbitrary. We could probably already get by with 4x8 32 hour weeks at the same pay. People won't buy your shit, but they also won't have a need for it. (see paragraphs below)

AI will replace jobs, a ton of them. But if AI does it's job and discovers better and efficient energy sources, we (humans) probably won't have to work a whole lot. Energy is the true commodity and that should be becoming even more apparent as we see AI sucking up MASSIVE amounts of energy right now. The transition between now and needing to work very little is the challenge we need to survive.

What you really want is a Star Trek type world. They don't have to work and don't really lack for things. At some point people might work because they want to, not because they have to. As you experience more VR and better VR, it will become apparent you really don't need more than your mind to experience and enjoy life. You might find it as crazy as people before computers would think we would be describing our current tech world but I really don't think we need our bodies. All we need is whatever stores our consciousness (maybe the brain but who knows). The entirety of the rest of your senses can be simulated and you won't know the difference. I've said it before but I'd be the first to upload my "consciousness" into a server. I don't give a damn about my physical body, and care even less about it each passing year. My body can't function at a high level anymore but I can 100% remember what it felt like to run fast, to throw a baseball at high speed etc. I remember the feeling even though I can't actually do it anymore. I'm thinking in the future, humans will be able to experience that 100 percent in their consciousness, even the exhaustion etc (if you want to feel that).

Energy and medical advances. I do think AI will make huge advances in those areas. The concern is that it finds a really easy way to exterminate humanity. Not that AI would do it, but the reason we still exist is that it's difficult enough to make a nuclear bomb that your average psycho can't do it. If AI discovers easier ways to make destructive things, it could be a problem because humans are so unstable it just takes 1 in 10 billion to do the wrong thing if there's an easy way discovered to exterminate life on Earth. The other concerning thing is encryption. There was a temporary scare that AI had figured out how to decrypt our best encryption, meaning nothing would be safe, bank accounts, nuclear codes, etc. They thought AI had created it's own math to do this. Turns out this was false but when we go from Artificial General Intelligence, to Super intelligence, we aren't going to understand what AI is doing, it will be beyond us (the smartest humans, comparable to if Einstein was talking to a chimp).

I'm giving AI/Humanity a 50/50 chance. 50 percent chance it ends humanity, 50 percent chance it launches Humanity into the next level. That may seem like not great odds, but I think it's actually better odds than not having AI considering the state of the world and our track record.

I'm OK with a coin flip at this point for our future. You'd have to convince me otherwise that we have better odds than that without AI.

[Funkmasterr]

I'm somewhat concerned I might have mildly fucked my motherboard today. Bought a second NVME and installed it, which requires removing my GPU. I pushed down the release for the card and it seemed to release a bit aggressively (I used a screw driver because it's the only way I can do it without pulling my CPU fan off). I couldn't the mechanism to latch onto the video card just by pushing the card into the slot - I had to pull the heatsink off of my CPU to have more access to it, and had to manually pull the latch up. Everything seems to be functioning fine, so I guess we'll see.

[Winnow]

I'm somewhat concerned I might have mildly fucked my motherboard today. Bought a second NVME and installed it, which requires removing my GPU. I pushed down the release for the card and it seemed to release a bit aggressively (I used a screw driver because it's the only way I can do it without pulling my CPU fan off). I couldn't the mechanism to latch onto the video card just by pushing the card into the slot - I had to pull the heatsink off of my CPU to have more access to it, and had to manually pull the latch up. Everything seems to be functioning fine, so I guess we'll see.

The little plastic release lever is the worst design. While removing my 3080ti for my 4090 I had a hell of a time accessing that little lever. I also used a screwdriver and it slipped multiple times with the screwdriver hitting my motherboard pretty hard a few times. Apparently it didn't harm anything but I hate that PCI lever. It's not user friendly unless you haven't installed anything else on your motherboard.

On one of my earlier builds that PCI lever broke off and I was happy it did. It made replacing the GPU so much easier.

I recently replaced 4 sticks of RAM to go from 32GB to 128GB and had to deal with those levers going behind my huge CPU heatsink/fan. I had to take one fan off to reach the the RAM slots but managed to not break anything.

Your MB is probably OK but there is always a chance of breaking something.

[Funkmasterr]

Yeah, there has to be a better way to design a release for this. At least one that doesn't involve me taking half the shit off of my MB to install a drive

Thanks for the reassurance. Everything still seems fine so I'm sure it's good. On the plus side, I now have 2 4TB NVME drives, so space shouldn't be an issue anytime soon.

[Aslanna]

Seeing reports about 13/14 gen Intel processors having some issues. So you might want to look into that if you haven't already!

[Funkmasterr]

Seeing reports about 13/14 gen Intel processors having some issues. So you might want to look into that if you haven't already!

I saw something about the I9 processors having issues due to the various motherboard settings that dramatically over-stress them. I had already shut that stuff off for mine, and have used the MSI setting (I can't recall the name of the setting) to reduce things a bit further even. So I think I'm safe, but I appreciate it, I'll look a bit more just to be sure there isn't something else I should be considering.