923
DuckDuckGo is down. Is there any info about it?? [EDIT: IS BACK] (lemmy.world)
submitted 2 years ago* (last edited 2 years ago) by to c/technology@lemmy.world
289 comments fedilink hide all child comments
 

Update: https://www.bleepingcomputer.com/news/microsoft/microsoft-outage-affects-bing-copilot-duckduckgo-and-chatgpt-internet-search/

It's also important to note that ChatGPT internet search and DuckDuckGo are experiencing similar issues because they use the Bing API.

UPDATE 2

20240523_210619

you are viewing a single comment's thread
view the rest of the comments
[–] 9 points 2 years ago (1 child)

That’s a nice hobby

I would suggest you to install a local instance of a LLM (mistral or llama3 for example) to widen your source of information. Go straight to Wikipedia instead of “googling” it if you don’t already.

Anyway, I didn’t know about kagi so I might take my own advice and give it a try.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 8 points 2 years ago (2 children)

    How big are they, and what do I need to use them well?

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 4 child comments
    •
  • [–] 2 points 2 years ago* (1 child)

    Most of 7b-8b models run just fine in 4bits quant and won’t use more than 4 or 5 GB of VRAM.

    The only important metric is the amount of VRAM as the model must be loaded in VRAM for fast inference.

    You could use CPU and RAM but it is really painfully slow.

    If you got an Apple Silicon Mac it could be even simpler.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] 2 points 2 years ago (1 child)

    I have an Intel Celeron Mobile laptop with iGPU and, I think, 256MB VRAM. How many bs does that get me for the LLM?

    Only half-joking. That's my still functional old daily driver now serving as homelab

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •