Adding here an example of what I was going for: entrepreneurs4nsf.formstack.com/forms/petiti...

Adding here an example of what I was going for: entrepreneurs4nsf.formstack.com/forms/petiti...

I wish more authors of papers I have missed citing would email me. At the same time I have only done this sparely and mostly with people I already know first hand or had some kind of interaction in the past and in no case I believe this was deliberate. It is just hard to keep up sometimes.

Thanks CVPR for bringing the conversation here

We just have to believe

But if it does happen in the open, my hope is that it’s a concerted effort that includes academics as much as a larger coalition of people who agrees this issue is important.

There should be pushback publicly but it should not be only self serving. If people only express concerns when it directly affects them that’s a sad state of things.

Indeed I don’t feel that way. I think there should be pushback but I also think the general public should be as concerned. Complaining and pushing back will happen but maybe not in the open.

That said there's no reason to not continue using our institutional channels to continue championing science and education.

One thing we can do going forward is to work so that the general community gets convinced why funding science and having strong research institutions is a good thing. This time we might have to learn from our mistakes.

Great times for innovation ahead!

These are models that can perfectly be run on most cheap hardware unlike the full large R1. But I wouldn’t be surprised we will see R1 quality running on more accessible hardware.

Everyone concentrates on o1 and R1 but even the base 7B or 1.5B models seem better than the very first public version of ChatGPT (3.5-turbo) that took the world by surprise.

Link to arxiv preprint: arxiv.org/abs/2412.15191