Magnetic core memory final form were single large perforated plates with many conductors plated on the ferrite surface through-holes, and only the vertical stack of bus wires were threaded through the plates. This meant weaving was less of an issue, and higher >1kiB modules were feasible in a smaller area. The main draw back is it sill had destructive read-once access, so always had higher latency in addition to being slow.
The DDR market will adapt, as China grey market state fab smells the opportunity. They have been counterfeiting cmos chips for decades already, and dram is not as complex as people like to assume.
Neuromorphic computing will likely kick over the LLM sand pile at some point, and all that discounted hardware will need re-homed. We can wait for the bubble to run its course, and actual investors realize they were conned. =3
> Neuromorphic computing will likely kick over the LLM sand pile at some point, and all that discounted hardware will need re-homed.
I don't see a lot of work going on in neuromorphic - there was some work at Intel, IIRC. Not saying you're wrong, but just wondering where you think it's going to come from?
> just wondering where you think it's going to come from?
Will likely evolve like any regular biological system, and consume translated LLM weight sets into its initial training condition 3D propagation structure.
The speed at which this occurs will likely initially be measured in weeks due to slower growth state writes, but once bootstrapped the GC is self-propagating.
I normally don't like to speculate, but the barrier to entry would actually be much lower than traditional silicon fabrication processes. It was an old idea from science fiction, that until recently was highly impractical. Asimov was likely wrong about the physical process, but not about how it is made.
Due to theoretical constant morphological changes under GC, one must acknowledge the inherent lack of safety such systems would pose. Have a nice day. =3
I expect you'd carry out most such work in the form of simulations, only moving to hardware once you'd demonstrated an efficient algorithm. If I'm right about that then it would be easy for any corporate R&D on the topic to fly under the radar indefinitely.
On the academic side of things there's a steady drip of papers on things like spiking neutral networks so I'd say the general theme is being explored.
I figure if a breakthrough happens it will be overnight just like what happened with transformers.
The next big shift will be HBF. All that DRAM holding essentially static weights that are read in nice, long linear reads in inference machines is wasted; if you had a proper interface to it you could replace it all with flash for a tenth of the cost.
I do but my days in the fab taught me that you do NOT want people to do this, considering the extremely dangerous chemicals involved. People have died changing EMPTY tanks of phosphine gas used for doping… and HF acid used for etch is another nightmare entirely.
I used to graduate at an institute having physicists as well as chemists, I gues it was no coincidence that only physicists operated with HF, one chemist told me that no chemist in their right mind would touch it
That's not quite accurate (but close enough). We had HF in the chem lab. It lived in a dedicated metal box with a massive neon warning label and a padlock.
It's notable in comparison that all the deadly organics lived together in an unlocked cupboard (vented OFC). I think the only thing I ever saw treated as more of a pariah than HF were radioactive isotopes. Those generally get an entire dedicated room with restricted entry and a tedious mandatory cleaning procedure.
Makes sense. HF deserves the same awe as radioactive material. I've always found both fascinating. Like some kind of dark magic that curses you if you contact it.
HF is routinely used in analytical labs; it's standard to microwave HF solutions for ICP digestions. It's not even the most hazardous reagent in my lab right now.
Now, perhaps this chemist meant that no chemist in their right mind would physically touch HF--in that case, I agree completely!
I visited a pcb making factory once. Left with an appreciation for the amount of work needed for 80-layer pcbs, and knowing I would not want to deal with making them myself.
my goal was simple 2 sided pcbs, machined traces because i wanted to avoid chemical etching, but when it comes to via's chemicals are really the only way. The chemcials needed for plating via's are very toxic. my current thinking to avoid the really nasty ones is to try conductive ink (probably pretty bad too) but it maybe would work to coat the fr4 material and then allow a copper plating to take... really it's a fun process machining and laser the soldier mask.
I keep thinking that for home tinkering this is really the wrong approach. Surely there are other more DIY-friendly ways to make switches besides with semiconductors? Sure, they wouldn't achieve anywhere near the same density as SOTA semiconductors, but that's not really possible at home anyway.
I guess you could always go back to electromechanical relays. I wonder if it might be possible to come up with a method of 3D printing those?
But in practical terms the Z80 was a 4 um process node so unless you're willing to go back to the proverbial stone age it seems like you need semiconductors and lithography.
It is only half as bad as working in the places that make tbose chemicals for use in clean rooms. Swaping out "empty" phosphine tanks is bad, but filling and shipping hundreds of full tanks is worse.
This is the issue I have with people saying that solar power is "clean and eco friendly".
It sure is, if you ignore the fact that you have to have a factory to make it where one of the *nicest* things around is the fucking hydrofluoric acid, and most of the rest will kill you instantly in trace amounts.
The technology is, the production is not but you can contain that, at least in theory. Compare that with gasoline that everytime you obtain energy from it you burn it out of existence and create a mess of the environment.
This is why we should have converted all the cars to run on propane, instead of scrapping them in favour of "cleaner greener diesels" 20 years ago when they started all the "scrappage scheme" bollocks.
The propane is going to get burnt anyway. May as well extract some useful work from it, and when you run a car off it they become ultra low emission.
No. Silicon oxide (glass) is extremely tough from a chemical perspective. That's why it's used in chemistry for everything. Barely anything touches it. Also this is the main reason I think that the meme of "silicon based life" is completely absurd and comes from people who only took high school chemistry and built their worldview on that.
Is it conceivable that some organic solvent could be synthesized that is, simultaneously harmless to water-based biological life, and capable of etching Silicon oxides?
Not really. Organics don't really have any affinity for this type of compound. You could, of course, create some kind of organic fluorinating compound, but it would basically just put you back at square one for safety.
No acids at all? That would be stupendously difficult for no real benefit. So many things are acids, so many useful reactions involve acids, and there's not a significant correlation between "is an acid" and "danger".
https://dl.acm.org/doi/10.1145/3173574.3174105