Comment by ChuckMcM
3 days ago
I think this is an important step, but it skips over that 'fault tolerant routing architecture' means you're spending die space on routes vs transistors. This is exactly analogous to using bits in your storage for error correcting vs storing data.
That said, I think they do a great job of exploiting this technique to create a "larger"[1] chip. And like storage it benefits from every core is the same and you don't need to get to every core directly (pin limiting).
In the early 2000's I was looking at a wafer scale startup that had the same idea but they were applying it to an FPGA architecture rather than a set of tensor units for LLMs. Nearly the exact same pitch, "we don't have to have all of our GLUs[2] work because the built in routing only uses the ones that are qualified." Xilinx was still aggressively suing people who put SERDES ports on FPGAs so they were pin limited overall but the idea is sound.
While I continue to believe that many people are going to collectively lose trillions of dollars ultimately pursuing "AI" at this stage. I appreciate the the amount of money people are willing to put at risk here allow for folks to try these "out of the box" kinds of ideas.
[1] It is physically more cores on a single die but the overall system is likely smaller, given the integration here.
[2] "Generic Logic Unit" which was kind of an extended LUT with some block RAM and register support.
Of course many people are going to collectively lose trillions, AI's a very highly hyped industry with people racing into it without an intellectual edge and any temporary achievement by any one company will be quickly replicated and undercut by another using the same tools. Economic success of the individuals swarming on a new technology is not a guarantee whatsoever, nor is it an indicator of the impact of the technology.
Just like the dotcom bubble, AI is gonna hit, make a few companies stinking rich, and make the vast majority (of both AI-chasing and legacy) companies bankrupt. And it's gonna rewire the way everything else operates too.
>it's gonna rewire the way everything else operates too.
This is the part that I think a lot of very tech literate people don't seem to get. I see people all the time essentially saying 'AI is just autocomplete' or pointing out that some vaporware ai company is a scam so surely everyone is.
A lot of it is scams and flash in the pan. But a few of them are going to transform our lives in ways we probably don't even anticipate yet, for good and bad.
I’m not so sure it’s going to even do that much. People are currently happy to use LLM’s, but the outputs aren’t accurate and don’t seem to be improving quickly.
A YouTuber watch regularly includes questions they asked Chat GPT and very single time there’s a detailed response in the comments showing how the output is wildly wrong from multiple mistakes.
I suspect the backlash from disgruntled users is going to hit the industry hard and these models are still extremely expensive to keep updated.
3 replies →
Dollars are not lost; they are just very indirectly invested into gpu makers (and energy providers)
[dead]
> Xilinx was still aggressively suing people who put SERDES ports on FPGAs
This so isn't important to your overall point, but where would I begin to look into this? Sounds fascinating!
Well this was the patent they were threatening with as I recall (https://patents.google.com/patent/US20030023912A1/en) and there was this one too: https://patents.google.com/patent/US5576554A/en
Basically the "secret sauce" of the startup recruiting me was that they were going to do wafer scale FPGAs that could be tiled together to build arbitrarily complex systems like military phased array radars and such. All very hush hush but apparently they had recruited some key talent from Xilinx which was annoying Xilinx.
Not OP but I was curious too. Here's all I could find that seemed related: https://www.businesswire.com/news/home/20200121005582/en/Xil...
Any thoughts on why they are disabling so many cores in their current product? I did some quick noodling based on the 46/970000 number and the only way I ended up close to 900,000 was by assuming that an entire row or column would be disabled if any core within it was faulty. But doing that gave me a ~6% yield as most trials had active core counts in the high 800,000s
I could guess that it helps with heat dissipation/management. But I don't know. That guess is from looking at the list of patents[1] they have.
[1] https://patents.justia.com/assignee/cerebras-systems-inc
They did mention that they stash extra cores to enable the re-routing. Those extra cores are presumably unused when not routed in.
That was my first thought but based on the rerouting graphic it seems like the extra cores would be one or two rows and columns around the border which would only account for ~4000 cores.
1 reply →
"While I continue to believe that many people are going to collectively lose trillions of dollars ultimately pursuing "AI" at this stage"
Can you please explain more why you think so ?
Thank you.
It's a hype cycle with many of the hypers and deciders having zero idea about what AI actually is and how it works. ChatGPT, while amazing, is at its core a token predictor, it cannot ever get to an AGI level that you'd assume to be competitive to a human, even most animals.
And just as every other hype cycle, this one will crash down hard. The crypto crashes were bad enough but at least gamers got some very cheap GPUs out of all the failed crypto farms back then, but this time so much more money, particularly institutional money, is flowing around AI that we're looking at a repeat of Lehman's once people wake up and realize they've been scammed.
Those glorified token predictors are the missing piece in the puzzle of general intelligence. There is a long way to go still in putting all those pieces together, but I don't think any of the steps left are in the same order of "we need a miracle breakthrough".
That said, I believe that this is going one of two ways: we use AI to make things materially harder for humans, in a scale from "you don't get this job" to "oops, this is Skynet", with many unpleasant stops in the middle. By the amount of money going into AI right now and most of the applications I'm seeing being hyped, I don't think we have have any scruples with this direction.
The other way this can go, and Cerebras is a good example, is that we increase our compute capability and our AI-usefulness to a point where we can fight cancer and stop/revert aging, both being a computational problem at this point. Even if most people don't realize it, or most people have strong moral objections to this outcome and don't even want to talk about it, so it probably won't happen.
In simpler words, I think we want to use AI to commit species suicide :-)
2 replies →
All the big LLMs are no longer just token predictors. They are beginning to incorporate memory, chain of thought, and other architectural tricks that use the token predictor in novel ways to produce some startlingly useful output.
It's certainly the case that an LLM alone cannot achieve AGI. As a component of a larger system though? That remains to be seen. Maybe all we need to do is duct tape a limbic system and memory onto an LLM and the result is something sort of like an AGI.
It's a little bit like saying that a ball bearing can't possibly ever be an internal combustion engine. While true, it's sidestepping the point a little bit.
> And just as every other hype cycle, this one will crash down hard.
Isn't that an inherent problem with pretty much everything nowadays: crypto, blockchain, AI, even the likes of serverless and Kubernetes, or cloud and microservices in general.
There's always some hype cycle where the people who are early benefit and a lot of people chasing the hype later lose when the reality of the actual limitations and the real non-inflated utility of each technology hits. And then, a while later, it all settles down.
I don't think the current "AI" is special in any way, it's just that everyone tries to get rich (or benefit in other ways, as in the microservices example, where you still very much had a hype cycle) quick without caring about the actual details.
8 replies →
While I basically agree with everything you say, I have to add some caveats:
ChatGPT, while being as far from true AGI as the Elisa chatbot written in Lisp, is extraordinarily more useful, and being used for many things that previously required humans to write the bullshit, like lobbying and propaganda.
And Crypto... right now BTC is at an historical highest. It could even go higher. And it will eventually crash again. It's the nature of that beast.
Why do you think that an AGI can't be a token predictor?
8 replies →
it cannot ever get to an AGI level that you'd assume to be competitive to a human, even most animals.
Suppose you turn out to be wrong. What would convince you?
9 replies →
I would guess you're not asking a serious question here but if you were feel free to contact me, it's why I put my email address in my profile.
Why are you assuming bad faith?
6 replies →
Really sorry, if the question came as snarky or if otherwise. Those were not my intent.
Related to AI given all around noise, really wanted to understand kind of contrarian view of monetary aspects.
Once again, apologies if the question seems frivolous.