Very nice. Be safe out there when tweaking these things.

Yes everything needs an initial condition.

You could have the smartest human political operator, but if he has no context, no motivation, not much is going to happen.

I'd call it interpolation on a high dimensional manifold. Convex hull is too simple a shape.

But yes, metaphorically I think that's right.

The other side of peak woke

Yes the problem is very hard. Mainly because high DOF generalization is very difficult.

We have self driving cars because what are the control inputs? Pedal, brake, steering wheel. This already took many many years.

Now for a humanoid robot: An action space that is metaphorically Hilbert. (Physically, yes, obviously)

Also, IMO, LLM's can aid the development of robots, but do little beyond a planning, human control interface. Below that it's the domain of control and the solution will be the correct combination of classical, neural, and real time optimization based control.

All the bad-ass biped robots that actually look natural? It's PID controls wrapped with control barrier functions constraining the QPs that are being solved in real time.

But that's annoying to derive per-application. So we'll need neural methods which can be learned (while being constrained by a priori knowledge of dynamics). My hunch is that the Yann LeCunn type of jepa models will be how tasks can be learned.

> All the bad-ass biped robots that actually look natural? It's PID controls wrapped with control barrier functions constraining the QPs that are being solved in real time.

That's not entirely true. Locomotion is well addressed by RL in sim. It's true that there is still a PD layer, and the RL policy produces setpoints for it.

>Yes the problem is very hard. Mainly because high DOF generalization is very difficult.

>We have self driving cars because what are the control inputs? Pedal, brake, steering wheel. This already took many many years.

Its actually amazing to me that this hasn't been solved yet. Its really not that hard of a problem.

Modern robotics, including self driving, are famously all about end-to-end training. We are trying to replicate what humans do through muscle memory. But muscle memory is not what makes us good at operating in the physical world. The thing that matters the most is our ability to simulate the world around us in a compressed form into the future, which lets us predict how our inputs will affect the world.

A similar system in a self driving car should be able to drive perfectly without self inflicted accidents 100% of the time, especially with basic lidar to serve as an error correction mechanism to the camera 3d scene reconstruction.

I don’t think the complexity scales with every additional degree of freedom like you are painting here. I think it’s just a matter of getting the right training data in sufficient quantities for an LLM to output across all degrees of freedom simultaneously without it being some exponential leap.

> So we'll need neural methods which can be learned

Data is a problem. LLMs had the advantage of the whole internet to train on. Robots don’t have that corpus of information. And real time learning seems to be something that everyone in AI is studiously ignoring.

The hope is that RL in simulation can fill the gap.

Also there’s imitating humans, via a suitable mapping from the human sensor, control and configuration space to the robot’s. Some groups have gathered video and other data from humans doing tasks, for example with a VR headset.

Me too

I started manual coding again at least 1 day a week.

Its good for the brain, but man it's really slow.

And the AI results prove it: Over the past couple years I've been able to bring several work projects to completion single handedly.

Our R&D company is now handling more clients and we are returning better outcomes/products faster than before.

So...what to do? Results don't lie.

However I will say LLM's can't write multi threaded double buffers by them selves. Probably because they are so application specific.

But I think the reason I can go do fast is because I went so slow before. I have an intuition I can transfer into an LLM. Question is if that intuition will become sloppy as time goes on...

I used to work there. The product is legit with a well established production line. Hundreds of aircraft in supply awaiting validation and testing.

I wonder how much his stock vested in his 4 years. Could be he vested 10%, is happy, now will move on?

Nice, I'm wondering what his new gig is. Since product is legit and he's not retiring, there is something better. Something AI I guess?

Man marketing really screwed a great engineered product.

4k resolution mouth camera?? That's why we go to a dentist every 6 months because I wouldnt know wtf im looking at.

"Oh there's that canker sore I feel. Huh, at least I can see it"

Bruh, you don't need a camera for gap detection. Just stick an IR sensor, detect change in light. Boom, $0.05.

dentists made up the 6 month rule. There's no evidence that it improves outcomes, for most people with healthy teeth, 24 months is fine:

https://pmc.ncbi.nlm.nih.gov/articles/PMC7701991/

healthy teeth are not the same as healthy gums, or oral health as a whole.

my dentist wants me coming quarterly

Bit off topic, but if you suffer from canker sores, SLS (sodium lauryl sulfate) is a known contributor to that in some people (me included).

It's a bit hard to find toothpastes without it that aren't also fluoride free, but they exist.

On the same topic, it's been a while since I have tried to find the best product to treat canker sores, but I have never found anything better than solutions composed of carboxylic/mineral acid and alcohol, and even then, it hardly suppresses the pain and I have found the treatment time to be about the same whether I apply something or not. The dream would be to have something that make them disappear near instantly.

tl;dr: ibuprofen may be a cause as well.

I suffered from incredibly painful month+ long lasting chronic canker sores (technically apthous ulcers) for the first 3 decades of my life.

Doctors and dentists suggested all the usual triggers (avoid SLS, supplement with B vitamins, etc)

Then one day someone mentioned the connection of NSAIDs and ulcers, and I instantly realized mouth ulcers are.. ulcers...

I used to use ibuprofen occasionally, often enough to not correlate it to canker sores. Of course then I’d use more ibuprofen for that pain, get more canker sores, and be miserable for months.

Haven’t bought ibuprofen for 10 years now and they just stopped. I have used ibuprofen on a couple occasions since I learned this and both times I developed a canker sore. IANAD, YMMV, I’m just happy they’re gone

>I wouldnt know wtf im looking at.

The camera is for the ai: "Dyson's Gap Optical Targeting™ prevents plaque formation by detecting the gaps and jetting between teeth every time you brush.²"

Presumably AI is going to process the images and detect issues and suspicious changes.

On paper it looks like a solid application of vision models.

Poor buddy looks like he's got the shakes