nalzok

Joined 7 years ago

Karma
37
Submissions
37
Member since
Mar 25
[ my public key: https://keybase.io/nalzok; my proof: https://keybase.io/nalzok/sigs/C-uZAs3m4gpLn0zA01ifxIdfq3RQfb3IuefNl9-iaCs ]
View on Hacker News

Recent submissions

Comment · 1 year ago
Comment · 2 years ago
I wonder what would happen if we quantized each dimension to 0.5 (or even fewer) bits instead of 1, i.e., taking 2 (or more) scalar components at a time and mapping them to 0 or 1 based on some carefully designed rules.
Comment · 2 years ago
I agree that Nix is the right idea, but I'm hesitant to adopt it right now because (i) rough edges like poor documentation and inconsistent interfaces make it feel immature, (ii) things are moving very fast with experimental stuff like flakes, which means it will take a while before Nix starts to stabilize, and (iii) recent community forks like Lix might create a fragmented ecosystem in the long run.

What are your thoughts on there concerns?

Comment · 2 years ago
Comment · 2 years ago
> by kqr, published 2024-11-19

It's from the future! ;)

Comment · 2 years ago
I wonder if this has anything to do with Apple Intelligence. Maybe they can have an LLM that operates on encrypted input text without decrypting it, so that users can send sensitive information to an Apple-controlled central server without worrying about privacy issues?
Comment · 2 years ago
Comment · 2 years ago
Comment · 2 years ago
Congratulations on the release! How can we download the model and run inference locally?
Comment · 2 years ago
Comment · 2 years ago
> Subjects: Computation and Language (cs.CL); Information Retrieval (cs.IR)

I'm surprised they didn't put `Machine Learning (cs.LG)` and `Machine Learning (stat.ML)`.

Comment · 2 years ago
Comment · 3 years ago

Live from the official Hacker News API

A modern reader for Hacker News · SvelteKit + Skeleton