what do people use for Neovim to integrate these models for tab-completion level of stuff. (i.e. non agentic/vibe coding)

I use llama.vim with llama.cpp and the qwen2.5-coder 7B model. Easily fits on a 16 GB GPU and is fast even on a tiny RTX 2000 card with 70 watts of power. Quality of completions is good enough for me, if I want something more sophisticated I use something like Codex

the most efficient languages are pretty unpopular, so this argument makes them even more efficient in reality?...

>We worked out a special arrangement so that this server is physically held by a long time contributor with a proven track record of securely hosting services.

Not clear if "contributor" is a person or an entity. The "hosting services" part make it sound more like a company rather than a natural person.

and HexOS I guess.

you can always make a new vector that's orthogonal to all the ones currently used and see if the inclusion improves performance on your tasks

> see if the inclusion improves performance on your tasks

Apparently it doesn't at least not in our models with our training applied to our tasks.

So if we expand one of those 3 things and notice that 17-th vector makes a difference then we are having progress.

>instead of spending massive compute rediscovering it from scratch every time

it's interesting that this paper was discovered by JHU, not some groups from OAI/Google/Apple, considering that the latter probably have spent 1000x more resource on "rediscovering"

https://www.androidauthority.com/graphene-os-major-android-o... hope fully soon

Main problem with this is that Google can end it as soon as they want to as Google effectively controls Android. Tactics like remote attestion will make it increasingly harder for Graphene to exist

(2018)

the note is written in Typst!

this using the flow [1] package

[1] https://typst.app/universe/package/flow/