c0g

I’ve been working on robotics for a few months now. I have built an arm, started receiving parts for my quadruped, and have learned enough RL to at least hold opinions on it (my background is ML/LLM training, so a bit different).

Eventual goal before I return to work next year is to have a robot I can take on walks with me that will pick up trash.

It’s a mobile platform, so saving 100 w on the CPU would make a difference. That’s the answer I tell myself, the real answer is because it would look hilarious :D

What’s the bottleneck? Once I’ve got the model and data onto the GPU my only cost is launching CUDA kernels right?

Not sure if that blog post is relevant, but even if it is it shows a 3060 gets //way// faster throughout than the igpu it is testing. I suppose I can test this myself by plugging my 3070 into the NVME on my desktop.

Does anyone have experience of putting a huge GPU on something like this and using it for inference? You'd be limited by data feeding over the NVME port, but otherwise you won't be bottlenecked right? Seems like a light weight and cute way to limit non-inference power/weight without having to pay the price of a Jetson board.

Any idea of DDP perf?

I’m originally from the UK, but it might still apply - it’s much more normal in the US to go straight to a specialist without a referral from a GP. If the company you’re moving with isn’t helpful you will probably be able to arrange directly with a GI doctor’s office with little effort.

Edward Huang with PAMF is the guy I go to, if you’re moving to the bay area.

There’s a cap on increases on the previously assessed value, value is re-assessed when ownership changes (except in certain cases like parents to kids). Look up Prop 13.

Given some tech companies are trying to move some jobs out of the Bay to compete less on salary, can I get hired at a lower pay satellite office then move to the Bay Area and get the salary bump?

If you wear a surgical mask, I found pushing it as high as possible to be the only thing that worked. You want the top at the same level as the nose bridge.

What's the latest IFR for Covid vs. flu? Last I read it was 1% vs. 0.1%.

Any whiteboard products? Collaborative drawing would make remote work lovely.