zen integrates every upstream change a few hours after release, it is built as a set of patch on top of firefox just to make that easy

they released a search engine where the model reads the first link before trying to answer your request

Revolt tries to be a discord clone/replacement and suffer from some of the same issues. Matrix happens to have a lot of feature in common, but is focused on privacy and security at its core.

The training doesn’t use csam, 0% chance big tech would use that in their dataset. The models are somewhat able to link concept like red and car, even if it had never seen a red car before.

The models used are not trained on CP. The models weight are distributed freely and anybody can train a LORA on his computer. Its already too late to ban open weight models.

Google uses their own chip for AI

They know the tech is not good enough, they just dont care and want to maximise profit.

Whatsapp is europe’s iMessage

You can take a look at exllama and llama.cpp source code on github if you want to see how it is implemented.

If you have good enough hardware, this is a rabbithole you could explore. https://github.com/oobabooga/text-generation-webui/

Around 48gb of VRAM if you want to run it in 4bits

To run this model locally at gpt4 writing speed you need at least 2 x 3090 or 2 x 7900xtx. VRAM is the limiting factor in 99% of cases for interference. You could try a smaller model like mistral-instruct or SOLAR with your hardware though.

Those slowndown article were clickbait / bad journalism , youtube hasn’t been slowing down the site for adblock user.

I put zorin on my parent’s computer 2 years ago, while its a great distro, their windows app support is just marketing, its an out of date wine version with an unmaintained launcher. Worse than tinkering with wine yourself.

It is already here, half of the article thumbnails are already AI generated.

It works with plugin juste like obsidian, so if their implémentation is not gold enough, you can always find a gramarly plugin.

It does not work exactly like obsidian as it is an outliner. I use both on the same vault and logseq is slower on larger vault.

It works pretty well. You can create a good dataset for a fraction of the effort and price it would have required to do it by hand. The quality is similar. You just have to review each prompt so you don’t train your model on bad data.

Do you use comfyui ?

Being able to run benchmarks doesn’t make it is a great experience to use unfortunately. 3/4 of applications don’t run or have bugs that the devs don’t want to fix.