Viewing profile — domenicrosati

Simulation? Like fluid dynamics. I heard that was CPU intensive.

Well done

Ya... those are not great places to start with him... as far as philosophy of science essays in conjectures and criticisms and objective knowledge are really great and much more ma…

Same

Well said. Attribution is important but it's impossible to know all the literature that is out there and even when you've tried your best to seek out prior arts there is always a p…

I wonder what software would be good for a logbook like this... I just use google docs for these kinds of things. Sure wandb and jupyter notebooks are good but they are not so good…

I am all for independent discovery but the author should know in the language modeling community we have known this for years [1]. The authors of DALLE are well aware of it. We hav…

Hey there - OP here. I haven't used spyder I'll have it check it out. The primary use case is: I am a researcher in nlp where speed of prototyping is key. I work in an environment …

Woah this is exactly what I'm looking for! Thanks

In 10+ years of startup experience on the science and engineering side. Sales fixes everything and is the hardest thing. If sales can execute then there is no problem. It seems obv…

The T0 series by big science is essentially an instruct model (though using multitask prompting instead of user feedback). You should check it out. I have got very competitive resu…

Cool! What motivated you to write it? I find the d2l implementation nice and simple as well https://d2l.ai/chapter_attention-mechanisms/transformer.html The one in pytorch itself i…

Be awesome if it were more comprehensive. I typed in d-serine, bromantane, nsi189, modafinil, phenibut with no results...

For folks who are interested. This is actually an already well studied topic! It is called "language complexity". The consensus is that in aggregate (all language artifacts like wr…

Is anyone able to find evaluation of these models besides speed and power consumption? I really cant find any baseline comparisons of accuracy and so on for any relevant datasets b…

Just anecdotally, Ive had a paper rejected once from arxiv. I am glad they did... it was not a very good one. Every other time thought has been fine

For brand name journals and conferences, yes they do. My experience with those is a very high rejection rate. There is a good reason to reject if you are not using a standard datas…

Be cool to see this for all the pokemon

I think the author is not doing a good job of presenting the research program behind ever larger language models. Many researchers are interested in the effects of scale on natural…

https://scite.ai does this as well (also citations are classified and analyzed whether they provide supporting or contrasting arguments to the citations) The scite extension also w…

Done https://github.com/scitedotai/scite-zotero-plugin