Viewing profile — rom1504

Why is a very good question indeed! My guess is we have not figured out how to include long term enough tasks into the RL training. As to whether they can today, it's pretty easy t…

I think the simple answer is LLM cannot do long term planning. Maintainability means thinking what will happen to this code in the next year and possibly hundreds of changes and ba…

yeah it's sad

Hehe, well you know, PR welcome, the front end is 500 lines https://github.com/rom1504/clip-retrieval/blob/main/front/sr... Other people have done a few alternate front ends alread…

yes indeed. Video is the clear next step.

Looks like you missed the whole point of this dataset. The idea that we proved is you can get a dataset with decent caption and images (that do match yes, you can see for yourself …

Done https://github.com/rom1504/clip-retrieval/commit/53e3383f58b... Using clip for searching is better than direct text indexing for a variety of reasons but here for example beca…

This is due to the aesthetic scoring in the UI. Simply disable it if you want precise results rather than aesthetic ones. It works for your example I guess I'll disable it by defau…

Hi, laion5b author here, Nice tool! You can also explore the dataset there https://rom1504.github.io/clip-retrieval/ Thanks to approximate knn, it's possible to query and explore t…

Yeah we have regular contact with many EAI members. EleutherAI is pretty great at open research.

Let me start by saying that laion is a non profit, open to anyone that want to contribute. Agreed about the website css. Do you want to contribute? What's the problem with the data…

a safe mode is now in place

That's interesting indeed! Note that the description search as well as the image search are both using a knn index on embeddings and not exact search. That helps for finding semant…

I wrote an overview of what methods and softwares are available for computer vision. Computer vision is really powerful these days !

For example the chakra engine has a better coverage of es6 than v8. see edge score there https://kangax.github.io/compat-table/es6/

So I tried it and it's 72135 bytes using tar czf (created by `fs.writeFileSync('/tmp/file',new Buffer(74207281).fill("1"),'utf8')`) Not that it's the most efficient representation …