This whole site reads like LLM-generated garbage. The domain was registered a week ago, yet it has random pages dated 2022: <a href="https://www.geekynews.org/0222blog" rel="nofollow">https://www.geekynews.org/0222blog</a><p>And… that page is plagiarized from <a href="https://www.ihg.com/crowneplaza/hotels/us/en/dublin/dblbl/hoteldetail/local-guide-whats-nearby" rel="nofollow">https://www.ihg.com/crowneplaza/hotels/us/en/dublin/dblbl/ho...</a><p>This looks to be a mix of stolen/plagiarized copy and LLM-regurgitated crap.
Serious question, how much money does SoftBank have to keep sinking into things?<p>My limited visibility to them usually doesn’t involve a lot of good news.
So, given that I'm already aware that I almost certainly won't understand any answers to this question, can someone give me a idiot level baseline as to exactly what an AI chip is and how it would differ from a cpu/gpu?
How much money does Son need to lose before he loses such liquidity?<p>More relevant to the article - I'm highly skeptical that our current architecture - LLMs in particular - will scale to AGI, let alone super intelligence. Humans in particular literally use orders of magnitude less energy and the smartest among us are still more capable. IMHO AGI, let alone superintelligence will require quantum computing getting somewhere, some sort of organic/biological computing or something else not invented yet.<p>Arm does seem like a natural fit, though. It seems everyone want to make their own chips these days.
ARM already have some "AI" IP, the Ethos NPU [1]. I work with a team that recently embraced it, replacing a custom in-house solution. I wonder if ARM will scale that up, or if their new AI division will go for something completely new. I wonder if it would be cheaper just to acquire a company like Tenstorrent instead.<p>[1] <a href="https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u85" rel="nofollow">https://www.arm.com/products/silicon-ip-cpu/ethos/ethos-u85</a>
How can they not? Did MS spin custom ARM parts with inference acceleration? And Apple has "neural processing" on their parts. And Qualcomm says the elite X is built for AI...<p>Seems like there are 2 plays here, there is inference training and then there is the end user inference acceleration. I expect they'll avoid the training side in gen1 but make some standard instruction additions that will become available on all ARM parts in the next couple years.