Which is also bad compared to 5.3 codex. People don't seem to realize that this is not codex 5.3 quality. It's a large step down on the benchmarks to get lower latency.

They don't even have GPU systems, so...no?

They have someone in the driver's seat

Or green contexts

800Gbps

you can do this with home assistant already

GBps

not true; there are a lot of simd instructions on GPUs

Such as?

dp4a, ldg. just Google it. there's a whole page of them

This is not true. GPUs are SIMT, but any given thread in those 32 in a warp can also issue SIMD instructions. see vector loads

That's quite an interesting way to explain why Apple does poorly in blind tests. The real reason though is that Apple's cameras are just not as good, but I suppose it's easier to explain away by making up biases.

My and your personal preferences for one camera over the other isn't the issue. Nor am I claiming that one is objectively better than another. My point is that blind tests (between two cameras of similar quality) are worthless simply because they don't reflect the preferences the test-taker would actually have given extensive use of each camera.

The issues with blind tests like this are well-known. I assure you I have no interest in persuading you to alter your own preferences.