• Some users have recently had their accounts hijacked. It seems that the now defunct EVGA forums might have compromised your password there and seems many are using the same PW here. We would suggest you UPDATE YOUR PASSWORD and TURN ON 2FA for your account here to further secure it. None of the compromised accounts had 2FA turned on.
    Once you have enabled 2FA, your account will be updated soon to show a badge, letting other members know that you use 2FA to protect your account. This should be beneficial for everyone that uses FSFT.

How AI will fail

DukenukemX said:
How video to ponder the "success" of AI.
Click to expand...
AI made video, with an AI sponsor.

Commitment to lease compute is a form of debt of course, for the next 2 decades, per year it is not that much and you do not pay interest on this either.

If expenditure according to the video is still lower than just cash flow, why say it is draining the volt ? The fact that it is not over 100% is exceptional because they have such exceptional cash flow, in any other industry that would be the norm to spend more than cashflow.

They mostly stopped to buyback shares and grow the cash reserve to finance it, they are able too because of the blackrock-blue owl-pimco and other that want to invest in the play (via those SPV).

Car makers do this for their factories, airlines do this for planes, telecom do this for tower network, it is not special (people that never look at stuff like that are just looking at it for the first time, because it is fancy name and AI).

Wall street of course if not fooled by something an youtube video will tell us, everything goes into their valuation including all those deals and all their implications, is resumed here:
https://www.spglobal.com/ratings/en/regulatory/article/-/view/sourceId/101652559

There is 2 think interesting in this video, according to the video
Big consolidater are:
) Spending less than cash flow still
) Everything they build is still considered to be quite profitable with positive margin

So everything according to the video is exceptionally great and nothing has to change, if like the video say new datacenter are still directly profitable like that by themselve in raw money.... you do not have yet to think do a still build barely-unprofitable one to build up some competitive advantage-not loose the edge to some long term calculator, that an easy yes.

Using the trick "generative AI" instead of AI in graph but not in talk to deceive ( it is not like a massive portion of the big tech pointed is the regular datacenter build out that is needed and would happened without GPT-3 or that generative AI is not now behind most of the giant traditional AI revenues that are content-ads)
 
Last edited:
Incorrect. AI revenue is negative, extremely far in the red. AI revenue != total company revenue.
 
w1retap said:
Incorrect. AI revenue is negative, extremely far in the red. AI revenue != total company revenue.
Click to expand...
for some company it is hard to distinguish, almost all Meta revenues are a funnel down of their use of AI ( it is their capacity of retention by creating/proposing content of targetting ads, those 2 things have been the 2 big source of AI revenues of the last 10 years and is still the biggest source of revenues).

LLM chatbot/api revenues, that a subset of AI revenues (that not all of what amazon, meta, google, walmart, spaceX/Tesla do with AI). Anthropic have been positive revenues for this the last 2 quarters (they get so much revenues and competitive demand for compute is so high tha tthey are not able to spend enough to stay negative like they should be doing).

Speaking on one side on total AI spend out and the other LLM chatbot/API revenues subset of the AI world alone is a bit of a trick to create content on the subject, content creator do to sell you an AI product in the video above...
 
1787010421826.png

https://www.cnbc.com/2026/08/13/cnb...-34-view-democratic-socialism-positively.html
 
https://www.facebook.com/CollectiveEvolutionPage

this facebook post a very long article on Micheal Burry, the guy who makes hundreds of million on short selling the MBS related stocks back in 2008. And on this article, Burry is shorting a good no. of names. Even if you don't agree w/ shorting AI stocks, have a look at his short selling list.


the real eye opener is near the end, where the writer of the article says:

AI is real, likely transformative, and the financial structure built on top of it can still be rotten.
Click to expand...
 
Last edited:
DukenukemX said:
South Korea stock market already crashed due to AI?
Click to expand...
Just FYI the crash in Korea was more due to leverage than AI in particular. Not trying to say that it means there isn't an AI bubble or anything, but the companies behind this market blow up have actually been having great profitability, because they aren't doing AI directly, they are selling the hardware and haven't done huge buildouts. Basically lots of people became enamored with a type of account that used leverage to get you 2x returns... the problem is that leverage makes downturns, even if temporary, much more problematic and increases the probability of you losing everything. If you want a decent (but long) video on it, Patrick Boyle has one that is pretty good.

So while it is AI related, it isn't really an AI market crash, it is people getting themselves in to leveraged positions that have to auto-sell on a daily basis when things go down and that creating a feedback loop that wiped a bunch of people out.

It's yet another example of that you shouldn't play with leverage, options, or any of the more complex financial instruments unless you understand the risk REALLY WELL. It shifts the curve such that the probability of a bad outcome is much higher.
 
Options Puts and Calls are purchase in cash. There is no margin allows on Options. The crash in Korea could very well be a margin of 70%, ie., they only need to put out 30% cash. So in the mth. of July, when SOXX tanks from 650 to 464, these investor got their margin call. And their loss can easily be higher than the actual cash they invested in. For e.g., if they invest $10K fully on a 70% margin, when that SOXX tanks about 200 pt., the investor will have a serious margin call. as they only pay 30%, so if 20% is $10K, they are out 70%, and the 1/3 SOXX tank will make them lost far more than 30%.

This is the reason w/ currency trade, in which the margin is 99%, so you only need to put out 1% cash, once a currency devalue or collapse , an average investor can't handle that kind of margin call
 
Go watch Boyle's video if you want more details but it was a special kind of account that basically did automatic leverage and settled and re-up'd on a daily basis. When things were going up it delivered as promised the double returns, but of course the downside is way more than 2x if things implode.

It wasn't options, I'm just using that as an example of another thing that has substantial risks people don't understand. Yes, the maximum risk is bounded by the purchase price, but the risk is how likely is it to pay out vs not, in which case you get zero returns. The "zero returns" is way higher than people tend to understand.
 
LukeTbk said:
AI made video, with an AI sponsor.
Click to expand...
Not sure how you figure Casual Finance uses AI, but the sponsor WhisperFlow claims to use AI... for speech to text.
So everything according to the video is exceptionally great and nothing has to change, if like the video say new datacenter are still directly profitable like that by themselve in raw money.... you do not have yet to think do a still build barely-unprofitable one to build up some competitive advantage-not loose the edge to some long term calculator, that an easy yes.
Click to expand...
At what point did the video say that datacenters are profitable? The point of the video is that AI companies like Meta create companies like Hyperion, to hide their debt so it doesn't effect their stock value. It's as if Meta expects AI to crash and don't want it effecting their stock value. Also, does nobody remember Hyperion from Borderlands 2? It's one of the many evil companies from that game, which Meta decided to name their Data Center.

View: https://youtu.be/VqvSXYotiAs?si=Fz---nq85JCq1D6p
 
It looks like he’s moving the table. “Just a liiiiitle more to the right!”

It also looks like the other three stumbled upon their dad’s porn stash.
 
"Disabled the TILT sensor" ... or maybe he is moving the A.I. machine blocking the soda pop cooler.

Speaking of cheaters. Weren't aim bots of the 90s in FPS game like Quake2 and Unreal Tournament an early form of A. I.? Those were only good with instant hit weapons. I remember being voted into a couple Q2 clans because I was not just another rail whore. Specialized in weapons that required timing. Like grenades and rockets.
 
DukenukemX said:
At what point did the video say that datacenters are profitable?
Click to expand...
When he said that new project have positive margin, I assume you did not actually watch the video (it is long), going from 40% operating margin down to 10% for the latest... is still all profitable and in very direct way, not in protection against competition-long term play-strategy type... those are all bonus over directly profitable infracstructure you are not even paying interest on building.

DukenukemX said:
The point of the video is that AI companies like Meta create companies like Hyperion, to hide their debt so it doesn't effect their stock value.
Click to expand...
that would only work if it was not 100% public, 100% known of the people that value the company, it is not something the maker of this video did found, it simply read their SEC stuff, everyone count it as debt like in their valuation of META.

Do you really think people at Goldman Sachs will watch the video, learn anything and have to re-evaluate their buying-selling point of Meta ? (and if that yet to happen it is because it has yet to be seen by big manager ?)

It does create some actual protection (i.e. the company can go bankrupt), clean entity for the private capital to invest in, it is not purely an hiding their debt move (except if by this we meant creating some protection of it), meta does not own much of that hyperion company so it is not that crazy that they do not own all of the debt, there is actual risk sharing going on.

The they cannot buy it using pure cashflow anymore they need investor and have investor is true, having investor instead of taking a pure loan do share the risk in some way and that do reflect in the way peopel account for it, they do count it as debt-like because of the amount of obligations, but no interest for a extremelly long term and a possiblity of independant bankruptcy in a vehicle is not the usual debt either. And when you look per year obligation, it is not that big versus the company revenues and/or the asset behind it.
 
Last edited:
Susquehannock said:
This is why I have A.I. trust issues.

A friend e-mailed me this image from their FB feed yesterday.
Click to expand...

Very annecdotale but just tried nano bana, openAI and grok with a simple:
make a vantage style picture (in colors) 50/60s, group of kids playing a game of pinball, clean dress and cut in a candy shop of that era

Nano banana did not had the issues, grok and OpenAI had it, when asked do you know what wrong with the image ?

Grok:
You’re right — looking closer, the boy in the red-and-white striped shirt does not have proper access to the flipper controls.
His hands are resting on the glass/playfield area rather than on the side buttons, and he’s standing more toward the middle of the machine instead of at the front playing position. None of the kids are actually operating the flippers from the correct spot; they’re all just gathered around watching and leaning on it.
That’s the issue you were pointing out. Want me to regenerate the image so one of the kids is clearly playing (hands on the flipper buttons, standing at the front of the machine)?

Or openAI when asked what wrong with the picture:
There’s also a physical/compositional problem: the boy supposedly playing is positioned awkwardly along the side of the machine. A player should be centered at the front/lower end of the cabinet, facing the backglass, with each hand naturally reaching a flipper button on either side. So the image superficially looks right, but the central object gives the game away.

The corrected one was quite good.

I.e. would you spend more money and compute, that the type of error the AI of today can catch and clear itself, using the AI validator loop is costly right now, but they get those errors and can tell the regenator what to do. (if you can manually ask it, what wrong ? knowing what wrong correct the image.... your AI loop can do the same)
 
1_rick said:
View attachment 820782
Click to expand...
I forget which AI I used for this, but I asked it to show me an image of what the Sega Neptune looks on it's side and this is what it created. It was so funny I had to keep it. It's for the Neptune project I'm working on but here's another photo of what it should look like. AI took the Sega Genesis Model 2 and wrote SEGA NEPTUNE on it and put all the ports on it's side. If anyone needs proof that AI doesn't actually think then here's your proof.
Gemini side view of Sega Neptune.jpg
real-functional-sega-neptune-game-console-1.jpg
 
You must log in or register to reply here.
Back
Top