Viewing profile — sirk390

I would use this as a human. That npm output is crazy. Maybe a better variable would be "CONCISE=1". For LLMs, there are a few easier solutions, like outputing in a file (and then …

All that complexity when you could simply do: 0 ? 'bg-colour-green' : 'bg-colour-red' %>">

> France ("consistently invested in nuclear for the past half-century" ). Not really and this is currenctly causing a big problem. France stopped building new reactors after 2002. …

Ruby is an excellent language/platform and you can do a lot more than using Rails. But yes I don't know for NLP.

Hi All, I build my first mobile app and wanted to show the first version: A second hand item local using AI to write text using only the images as input (using openai-vision-previe…

I you hang them at 45 degree the depth will be reducted by sqrt(2). (about 0.7 x hanger length), and you will lose space on each side. And the more you increase the angle, the more…

Better, but irrational numbers can have a predictable pattern like "0.110100100010000" ( E.g "0.1 10 100 1000 10000" )

For example you could set cookies before visiting another website. This is currently impossible in an iframe but possible in a browser. I've wanted to do this to automatically logi…

I really though you were going to say "Chat-GPT detected" when quoting that message.

With compositions A uses B but B can never use A. With inheritance Child can use the Parent, but Parent will also call the Child (virtual methods) which in turn can call the Parent…

Humans are pretty bad at these questions. Even with the simplest questions like "Sally (a girl) has 3 brothers. Each brother has 2 sisters. How many sisters does Sally have?" I thi…

> Whereas, in biological brains, the weights are updated continuously. My personal impression is that many "weights" are updated during sleep time. For example when training juggli…

In humans, sleep is also required fo learning, so it's not fully continuous. An AI that occasionnaly retrains using the new knowledge would still be very interesting.

It could be double speak, but the obvious thing you understand from this formulation it that he won because he is a philosopher. Not that he won, and by the way he is a philosopher…

lambdas are very useful for example for sorting data using a key function. Maybe the auther is saying that it should be called differently, or have a different syntax and the title…

Is outperforming GPT-3 still a good reference? It seems there are many models outperforming GPT-3 in the superglue benchmark: https://super.gluebenchmark.com/leaderboard/ GPT-3 is …

And if every parameter is one byte, the minimum, it will take at least 70gb to save or share this model. So it's still way to big to package directly in a app.

I doubt that there are numbers to prove that. SMR might just be a buzzword. From the page below there don't seem too many operating or under construction (5 operating, and 4 under …

Crazy, but who thinks AI is not moving forward? I don't think anyone on HN.

Most of the time it's not compute or memory intensive so any computer will do. The most important thing then is too have a good chair, keyboard and mouse!

Just don't lookup your private key in there. This would be like giving it to the website