Recent submissions

Comment · 20 days ago
Imagine not reinventing the wheel for no reason. But don't worry, I imagine that modern prompting techniques will be used such as "do not make mistakes" so everything will be fine (/s)
Comment · 3 months ago
Seems like it wouldn't work for different branches.

It probably needs to store the full F16 version for each model variant, even if the variants share the same base model

Comment · 3 months ago
It's just a wrapper around llama-quantize, i don't see why it wouldn't work.

Yet it's only useful if one wants to have both the F16 original model plus all the other GGUF quants at a time and doesn't mind spending compute every time they need a specific quant again.

It doesn't do much for a consumer who only needs one or a few specific quants that work on their hardware and I'd wager it's not something that multi billion dollar companies need. At least as far as I'm aware major llm providers aren't using gguf and llama.cpp to serve their inference

Comment · 4 months ago
Comment · 4 months ago
I love the naming of their new networking tools. Now there's pesto to go along with pasta
Comment · 4 months ago
Of course a 1000$+ windows laptop is going to look and feel like a low end 300$ one /s
Comment · 5 months ago
Seems likely, same for me.
Comment · 5 months ago
?
Comment · 9 months ago
The thing that makes the most difference is a drive being CMR vs an SMR one. CMR ones are recommended if you are ever going to write large-ish amounts of data in one go or if you ever plan to make a raid 5/ raid 6 arrays.

SMR drives are now what you find on most consumer drives between with capacities 1<x<8 tb (higher capacities too, but depends on the manufacturer) , they have a CMR area of the platter as a sort of write cache (like slc cache in ssds), while the rest of the platter will be really slow to write to. The write head is wider than the read head, so to overwrite something the drive has to first read and copy somewhere else the data on the track(s) that would be overwritten. This makes whole drive writes really slow and can kill raid 5/6 since resilvers would take very long, possibly even a month, instead of a few days.

Besides the recording technology, the color of the label and the product line name are mostly marketing and won't make too much of a difference for simple usage.

Comment · 9 months ago
Seems that the Spotify torrents are now unavailable until further notice. bummer
Comment · 11 months ago
They could also use MoltenVK
Comment · 1 year ago
99.38%
Comment · 1 year ago
That looks awesome!
Comment · 1 year ago
Will using rust on my Intel® Core™ 13th gen cpu cause it to oxidize?

This would be terrible, I thought rust was a safe language...

Comment · 1 year ago
Was it this one? https://marketoonist.com/2023/03/ai-written-ai-read.html

I know that it talks about only 1 and not 3 points, but it seems close enoguh

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton