Re:AMD acquires Taalas to boost inference performance by etc...
by nomel on Thursday August 06, 2026 @07:05PM
(#49203840)
No, the point is inference speed and power.
Re:AMD acquires Taalas to boost inference performance by etc...
by try-working on Friday August 07, 2026 @12:01AM
(#49205774)
you don't understand what I wrote.
Re:AMD acquires Taalas to boost inference performance by etc...
by nomel on Friday August 07, 2026 @01:44PM
(#49213848)
I do. The point is inference speed and power, making previously impossible local inference possible. A side effect of that hardware optimization is fixed capabilities.
You've confused engineering compromise for malice, and reversed the purpose. For the model capabilities and inference power draw, what alternative do you see to a (at least mostly) fixed hardware model?
Re:AMD acquires Taalas to boost inference performance by etc...
by try-working on Friday August 07, 2026 @04:28PM
(#49215824)
What I'm saying is that Apple will use these type of models etched into chips, and they will do it because it drives obsolescence, so they can shorten the upgrade cycle. They will do it because they figure out it's good for them.
Re:AMD acquires Taalas to boost inference performance by etc...
by nomel on Saturday August 08, 2026 @02:32AM
(#49219367)
You've confused engineering compromise for malice, and reversed the purpose. For the model capabilities and inference power draw, what alternative do you see to a (at least mostly) fixed hardware model?
Re:AMD acquires Taalas to boost inference performance by etc...
by try-working on Saturday August 08, 2026 @06:56AM
(#49220597)
No, you still don't understand what I'm saying. Yes, ASICs make inference faster, but also makes the hardware obsolete faster, if it's embedded in a phone. That sounds like a negative, but Apple is going to turn it into a positive for their business and use it to speed up upgrade cycles as cameras are no longer a driving factor and cycles have been getting longer.
i have written about this:
"For device makers
Packaging models with laptops and smartphones will let application access near free, low latency inference and potentially offer users a better experience with the option of preserving data on-device. This is viable under the condition that tasks that do require larger expert models that run in the cloud can be routed to external models. A side-effect of local models and what will let Apple cut upgrade cycles from ~4 years (?) down to 12-18 months is specialized hardware to run them. For almost a decade, smartphones have been trying to compete on better cameras. This coming decade will see them selling better GPUs, NPUs, ASICs and whatever other things they'll be calling the inference chips, to drive re-purchase. Every six months will see a better model on new hardware, which will enable better performance in certain applications."
https://try.works/role-model-the-case-for-a-model-routing-pr...