Viewing profile — evolvingstuff

That's interesting. My brain does the same in terms of attempting to simulate that model of the people, but when it becomes impossible to run the algorithm (too large of a group), …

Very excellent point. One simple possibility I could imagine to mitigate this would be having an additional device/button one had to physically press in order for the thoughts to b…

From the study: "It should be remarked that, in the majority of the cases, people adopting plant-based diets are more prone to engage in healthy lifestyles that include regular phy…

You are correct, that is an error in an otherwise great video. The k+1 token is not merely a function of the kth vector, but rather all prior vectors (combined using attention). Th…

I suspect in the near future there will be a number of cases where individuals will intentionally release a bunch of AI "chaff", in the sense that having a very large number of bad…

I love Nomnoml. I have lately been using it to visualize hierarchical tag structures in a browser-based PKM project I am working on. I find it creates fairly clean layouts. Example…

Why would RWKV have a particular advantage in this context? (I may be missing some key intuitions)

You have been shamelessly self-promoting your Hopf algebra/deep learning research on a very large percentage of posts I have seen on HN lately, to the degree that I actually felt t…

Easy. Have a setting where someone can consent to (or not) receiving images that may potentially have nudity in them.

I have found the books System Design Interview (volumes 1 and 2), to be really nice and informative reading material on this topic.

Maybe I'm missing something obvious, but this seems like a way to calculate a mode, not a median.

So I just googled "differentiable Monte Carlo" and it looks like that concept has so far only been applied to ray tracing, but I would be shocked if that (or similar) doesn't becom…

Thank you!

Completely agree! Plus, less trivially, there can be a bunch of different link weight settings (for an assumed distribution of inputs) that result in nearly-symmetric behaviors, an…

Here are some "animated" loss landscapes I made quite a long time ago: http://evolvingstuff.blogspot.com/2011/02/animated-fractal-f... These are related to recurrent neural network…

May have looked it up.

Back in the early 2000's (when I first started getting into this stuff), Schmidhuber's ideas were absolutely off-the-charts revolutionary compared to anything any other lab was doi…

If I remember correctly, a big advantage of particle filters over Kalman filters is that the particle filters can model complex, multi-modal distributions, whereas the Kalman filte…

I am acquainted with a person working on this: http://code.google.com/p/openworm/

Another fun fact about high-dimensional spaces: Randomly pick k points in an n-dimensional space. Now, find their average location. As the number of dimensions increases, it become…

Agreed. To elaborate: Saccades to an unexpected stimulus normally take about 200 milliseconds (ms) to initiate, and then last from about 20–200 ms, depending on their amplitude (20…

Only twice as unreasonable :)

One way the circumvent the need for 5000 teraflops mentioned in the article is to exploit the fact that our eye is only capable of seeing a relatively small area in great detail at…