Hacker Timesnew | past | comments | ask | show | jobs | submit | aarondf's commentslogin

My word... samwho is doing some of the best technical explainers on the internet right now.

Leading to my question: Ok keeping a zero and a minus-zero does make sense for some limits calculations... But when all you have is 4 bits, is this not quite wasteful? Would using the bits for eg. a 2.5 not improve the model?

It might be useful. The Lion optimizer uses 1-bit values to represent forward or backward. NNs can pick up on patterns like that in very strange ways. Of course, those are 1's, not 0's, so maybe the benefit disappears when multiplying by zero. But it's important to challenge assumptions like "well, let's get rid of the negative half of 0" before you test experimentally whether it's useful or not. NNs are nothing if not shockingly weird when you try to make them.

Oh well that's a rabbit hole: NVIDIA Blackwell has this, also GGUFs sidestep this with Qi_j / Qi_K... Great article, spikes curiosity!

Heartily second that! It was cool to see a combination of DOM, SVG, and canvas visualization all in use for this post.

I've run into that issue while developing https://soloterm.com.

If you respond twice to their theme query probes, the whole thing bricks. Or if you're slightly out of order. It's very delicate.


damn framerate looks good


And guess how you make friends in high(er) places...

by...

publishing your work and making friends in your industry


I don't know enough about different industries to know if this is true in general. But I do know in tech it is all about networking (aka soft nepotism): spending your career making friends ("swiping right on every work relationship"), and the fraction of those who go on to massively succeed you can then call in favors. At least that's how I made three huge jumps in my 35+ year career, and how the majority of my peers got the big step-functions in pay.

Perhaps in my original post I'm just confusing academia with industry, since I know so few academics.


Very well said


Hey! I wrote the article a few years ago. Fun to see it on HN again.

It was here back when I wrote it: https://qht.co/item?id=32071137

Lots of comments talking about how this is just some sort of ploy to feed the machine. I don't know what to tell you. I can only tell you it changed my life and the lives of many others. Hope it can help you too!


Sorry to say, but the article is complete BS. Publishing is only desirable when your work is top-notch ;)


You had me in the first half! <3


Then define luck as "connecting with fellow nerds." Still works


Totally. An engineer, who (at the the time) works in marketing! Makes sense to me :D


I'm a software developer who was, at the time, working in a marketing role. Happy to answer questions.


I wrote the article. I'm not a marketing droid, I don't work for GitHub, just a guy recounting his personal experiences and hoping to help others.


Guidelines | FAQ | Lists | API | Security | Legal | Apply to YC | Contact

Search: