I think Jevons Paradox and scaling laws will make this not the case. If bigger models are always better (which seems they are), then will always need high-end hardware.
Yes, objectively these characteristics of Japanese corporations seem like inefficiencies in the "free market".
Lack of mobility across companies (no price discovery on wages), lack of specialization (no focus), age based hierarchy (anti-meritocratic). None of these sound good for a well-tuned system.
I suspect much of Japan's stagnation is due to this system.
This model is very misunderstood. It's not good at raw generation, but it has really deep world knowledge. Not just knowledge of physics, but just knowledge in general.
There are examples like providing a basic google maps view and then asking it to simulate driving from point A to point B, and it will generate landmarks from that location.
It's also great at consistency and editing. Probably SotA in editing.
Not sure what use cases will be unlocked but I sense something is there.
I'm curious how the 6 months have looked from a non-programmer's perspective. What kind of co-working tools and similar optimizations have people from other fields experienced?
It's easy to praise Deepseek for its results and generosity -- how they can keep up with frontier labs on Huawei chips for a fraction of the cost! -- but let's not forget a big part of their toolkit is heavy distillation of SoTA.
Is the author suggesting people to have to live with going through a phase of being nocturnal? In the free running algorithm, we're supposed to sleep 15 minutes later each day until we're falling asleep at like 9AM?