It’s also important to note that ChatGPT internet search and DuckDuckGo are experiencing similar issues because they use the Bing API.
UPDATE 2
It’s also important to note that ChatGPT internet search and DuckDuckGo are experiencing similar issues because they use the Bing API.
Okay.
Now that we already know we are pretty much at the hands of one pupeteer, what options are there?
I already read about Kagi (apologies if mispelled) but I like to write as a hobby and 300 searches per month go fast.
What other options are there?
Edit:
For those who may be arriving now:
p.p.s Should I start categorizing these from “shady” to “worthy”?
p.p.s 2 Does anyone remember StumbleUpon? I know it was never a search engine to begin with but it was the best source of good internet content I ever got acquainted to.
Can we get something like that back?
SearXNG
This is the single most obnoxious name I’ve ever seen. But, the service could be good (I’ve never used it)
Basically the mother of all search engines. Merges Google, DuckDuckGo, Bing, etc. into one.
it’s a fork (Next Generation) of deprecated SearX project.
Mojeek is far from perfect, but also is 100% independent.
Thank you I tried Mojeek a few days ago but I forgot what it was called. the site for mojeek is mojeek.com btw.
Sometimes it’s a hard one to remember 😅
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.
How big are they, and what do I need to use them well?
Take a look at Ollama.ai, just follow the installation instructions. A decent GPU is recommended, and the models are around 10GB iirc.
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.
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 homelabWell, I got a good news and a bad news.
The bad news is you won’t do shit with that my dear friend.
The good news is that you won’t need it because the duck is back.
There’s also mojeek.com running their own index. Not perfect, but sometimes usable.
you can also send us in queries where we’re not perfect, or let us know elsewhere, and we’re keen on fixing them
That was unexpected, but welcome message. Thanks for caring.
There’s a new search engine called Yep, made by the team at Ahrefs, a SEO tool SaaS.
It looks promising because they have their own index, but it’s a bit slow sometimes.
ugh
I only tried one example, so the sample size is pretty small, but that search engine seems pretty bad. I tried looking up “rust bevy points” in both Google and Yep. The first Google result is a library to draw points in Bevy and the rest are pretty relevant. Yep simply doesn’t have that result at all and all of their results are just generic results about Bevy.
I tried DDG for the sake of comparison and it’s somewhere in-between. The results are mostly relevant and the “correct” result is still on the first page.
I jumped back on ecosia. It’s nice there, but I’m sure there are issues that a non tech person like me may not know about
Read somewhere on the thread Ecosia is part of Bing ecosystem.
It is. That or it was very coincidentally down for the exact amount of time as DDG.
Ecosia also uses Bing and was also down. That’s the one I use.
Just letting you know kagi has a family plan with unlimited searches, so you can probably split it with family or friends! I have yet to see how searxng search holds up to kagi.
Appreciate the edits
You’re welcome.
I run a searxng instance on my pi server, use it from all of my devices, honestly forget its a thing running from my office 99% of the time until I’m rebooting the pi for one reason or another and spend more seconds than I’d like to admit wondering why I can’t run a search 🤣😅
if you just hate western companies, there’s always yandex, supports more fringe contents as well, since russia moment.
But it’s Russian.
yeah, but it is another option if you don’t want to sell your data to big google. Plus it also has utility in other areas.
Worth consideration.
Hate requires too much emotional investment. What I want is options.
well good news for you! It’s also an option!
Was this news to you? Other than Google and Bing there aren’t any other significant alternatives. Even brave is a bit limited.
You can’t know everything.
Yes, I understand that, but still surprised. I thought it was well known that DDG used bing.
Today, I was the 1% getting to know something new.
You should add startpage.com to your list
Done!
Just pay the extra for unlimited searches. It’s not much money, especially if it’s a tool for work.
Listen sugartits, some of us don’t have much money. So if it’s not much money we still don’t have it
(Mostly i just wanted to point out your username by using it in a comment)
That was one of the most out of the blue comments I have ever read. It sounded so… unreal. Something out of a sitcom. Then I read “sugartits” is the name of the lemmy you were replying to. That’s was really top mark. Kudos for you.
It’s a hobby as it is.
If I ever manage to sell enough copies of it to be able to pay for a Kagi subscription, I’ll do it and make it public knowledge.
brave search is pretty good: https://search.brave.com/
Brave search is independent. It was trained with google search but now it’s a thing of its own and doesn’t rely on google. I switched from DuckDuckGo a year ago and haven’t looked back
Brave search is run by crypto bros. I’d rather use Kagi or DDG or even Google.
I would use Kagi if it was free. It might be run by crypto bros but doesn’t mean it’s a bad product. Google and bing own 99% of the search engine market. Competition that doesn’t rely on those two is always good
Well they were dishonest about the product behavior in multiple cases, such as adding referral links to search results. That makes it a bad product.
That is a much better argument. But I still use it because I finally get different results from bing or Google.
I agree they were, but that’s the benefits of open source you can call out companies for doing stupid shit. Just like when Mozilla adds unnecessary telemetry.
Brave products are not open source. Not their search, and not the browser. Your post wording seems to imply that it is.
The browser is open source (MPL)
Never knew that, thanks for the correction.
I know the search is not but I thought the browser was on GitHub
I stand corrected!
Lumping in Bing with Google is just unfair. Google controls like 90% of search. Bing is ~3.5%. Choosing duck duck go and helping that 3.5% is wayyyy better of a choice than supporting crypto bros.
https://gs.statcounter.com/search-engine-market-share
Personally I don’t want to support Microsoft bing either. This website you shared doesn’t lump together all the bing using search engines (DuckDuckGo and yahoo). How is supporting Microsoft a wayyy better choice. This isn’t some pump and dump scheme. Your criticism should be of the company (they added referall links to their browser and the owner has some nasty political takes on top of running another privacy invasive company).
It does not matter if it lumps them together or not. Google still has 90% and they’re not Bing. Yandax another ~3% and they’re not Bing. That means at max Bing is 7% if you combine the rest. 3.5% vs 7% does not change the root of my argument.
Those points you make against Brave are valid though. I just run into too many people who are in the Brave cult and it’s concerning.
trained? like AI trained?
Nope, like it used to index from google but now it doesn’t. DuckDuckGo gets all its results from bing
forgive my ignorance but why doesn’t it get its own results
No?
Yeah I was confused by that choice of words. Train is for ML and AIs. Search engines used to need crawlers to run regularly because, you know, shit changes.