Fitik

joined 2 years ago
[–] Fitik@fedia.io 3 points 3 months ago

With the launches of Mistral Small in March and Mistral Medium today, it’s no secret that we’re working on something ‘large’ over the next few weeks. With even our medium-sized model being resoundingly better than flagship open source models such as Llama 4 Maverick, we’re excited to ‘open’ up what’s to come :)

Seems like a large model will be coming soon as well, nice news

[–] Fitik@fedia.io 11 points 3 months ago

There's a whole community dedicated to this topic - !fedibridge@lemmy.dbzer0.com

[–] Fitik@fedia.io 6 points 3 months ago (1 children)

I like Every Door app, it makes it trivial to contribute and it's pretty nice

[–] Fitik@fedia.io 3 points 3 months ago

If you like Urbanism I recommend !transit@video.canadiancivil.com (@reece@video.canadiancivil.com ) and !urbanism@video.canadiancivil.com ( @ohtheurbanity@video.canadiancivil.com ) PeerTube channel, they're pretty high quality and their content is interesting

[–] Fitik@fedia.io 14 points 3 months ago

I think it's great news, I use Droid-ify, third party client, just because the official F-Droid app is not very good, and it could improve it a lot

[–] Fitik@fedia.io 6 points 3 months ago (1 children)

A great community btw, recommend joining, hope they won't lose much activity because moving

[–] Fitik@fedia.io 2 points 3 months ago (1 children)
[–] Fitik@fedia.io 8 points 3 months ago (3 children)

I am from the Middle east, so technically I am from Asia

[–] Fitik@fedia.io 2 points 3 months ago

It's already a thing btw, I've heard of "Status" multiple times already, but I think the OpenAI one is meant for people to communicate with each other

[–] Fitik@fedia.io 3 points 3 months ago

I recommend joining !newtolemmy@lemmy.ca , it seems more appropriate for such questions

[–] Fitik@fedia.io 4 points 3 months ago

Maybe sh.itjust.works or lemmy.sdf.org or lemm.ee? Or infosec.pub?

There's also discuss.tchncs.de that is focused on tech

[–] Fitik@fedia.io 3 points 3 months ago

I don't use Lemmy, I am reading this post on MBin

 

MIT research finds the brain’s language-processing network also responds to artificial languages such as Esperanto and languages made for TV, such as Klingon on “Star Trek” and High Valyrian and Dothraki on “Game of Thrones.”

 

What is it like to use PeerTube as a video creator? Spoiler alert: it's amazing!

 

Scientists have created the first map of the crucial structures called mitochondria throughout the entire brain ― a feat that could help to unravel age-related brain disorders1.

The results show that mitochondria, which generate the energy that powers cells, differ in type and density in different parts of the brain. For example, the evolutionarily oldest brain regions have a lower density of mitochondria than newer regions.

 

Gemini 2.5 is our most intelligent AI model, now with thinking.

 

A paralysed man can stand on his own after receiving an injection of neural stem cells to treat his spinal cord injury. The Japanese man was one of four individuals in a first-of-its-kind trial that used reprogrammed stem cells to treat people who are fully paralysed.

Another man can now move his arms and legs following the treatment, but the two others did not show substantial improvements. The trial was run by Hideyuki Okano, a stem-cell scientist at Keio University in Tokyo, and his colleagues.

 

In what's expected to soon be commonplace, artificial intelligence is being harnessed to pick up signs of cancer more accurately than the trained human eye. This latest AI model has a near 100% success rate and serves as a clear sign of things to come.

Study - https://www.sciencedirect.com/science/article/pii/S2666990025000059

 

Today we're opening a public beta for our social web integration in Ghost. For the first time, any site on Ghost(Pro) can now try out ActivityPub.

 

Today we announce Mistral Small 3.1: the best model in its weight class.

Building on Mistral Small 3, this new model comes with improved text performance, multimodal understanding, and an expanded context window of up to 128k tokens. The model outperforms comparable models like Gemma 3 and GPT-4o Mini, while delivering inference speeds of 150 tokens per second.

Mistral Small 3.1 is released under an Apache 2.0 license.

view more: ‹ prev next ›