This is like complaining that the mariadb team has failed to make their tech easy to use. It's a server side piece of software. There are plenty of user friendly GUIs or wrappers for it. lm-studio or unsloth are to llama.cpp as something like phpmyadmin is to mysql/mariadb.
Haha ok, like click & run sort of levels? They do package builds on their github releases depending on your architecture (CUDA or not etc.) so it should be close to "very lazy" levels of ease.
I find it useful, but the models I run are pretty rubbish due to my lack of RAM, which is a pity.
> It's like with latest vector of attacks being spamming Github with malware injected in proper looking code in hope of AI to index it.
First of all "malware" which is often technology working as intended happens at the OS level, not the github repo level. You can't say a repo is malware in most cases - it depends on the deployment. Second and more importantly, the vast majority of training data would have to reflect the "injected attack" for it to have any bearing.
There are ~30 keywords in JavaScript, compared to 100s of thousands in spoken/written languages.
You cannot "attack" anyone or anything through an LLM. It's an offline, read-only model of text, that's it.
It obviously won’t be continuous delivery but could make sense if the lifecycle of a model (train, deploy, iterate (meaningfully) is about 1-2 years. In that case it fits nicely in the “this year’s model” already established with cars, phones, etc.
What if we just normalized taking meth more often?
I got a drawer full of magnets and old shoelaces, let's make a projeck. You guys wanna do something extremely inefficient? Let's goo