608
submitted 1 week ago* (last edited 6 days ago) by MTK@lemmy.world to c/technology@lemmy.world

I suspect that this is the direct result of AI generated content just overwhelming any real content.

I tried ddg, google, bing, quant, and none of them really help me find information I want these days.

Perplexity seems to work but I don't like the idea of AI giving me "facts" since they are mostly based on other AI posts

ETA: someone suggested SearXNG and after using it a bit it seems to be much better compared to ddg and the rest.

(page 4) 50 comments
sorted by: hot top controversial new old
[-] Imgonnatrythis@sh.itjust.works 8 points 1 week ago

Why have you not tried Kagi? If it's important to you to have good search and you don't like being spied on and having ads shoved down your throat, it's worth paying a small fee for quality instead of paying with your privacy for crap results. It's been a breath of fresh air. Searching is fun again. It also indexes Lemmy. Traditional Search has largely gone to crap, but I'm tired of everyone complaining that these mega companies offering 'free' services aren't holding their end of the deal instead of supporting the people that are doing something about it. I'm not optimistic things like qwant or searx will be sustainable or deliver high quality results, but by all means donate to them with time or money if you believe in them.

[-] ScreaminOctopus@sh.itjust.works 6 points 1 week ago

Kagi is the same as ddg 99% of the time.

load more comments (1 replies)
load more comments (22 replies)
[-] ripcord@lemmy.world 8 points 1 week ago

Kagi is very good.

[-] j4k3@lemmy.world 7 points 1 week ago

I don't use perplexity, but AI is generally 60-80% effective with a larger than average open weights off line model running on your own hardware.

DDG offers the ability to use some of these. I use a modified Mistral model still, even though its base model(s) are Llama 2. Llama 3 can be better in some respects but it has terrible alignment bias. The primary entity in the underlying model structure is idiotic in alignment strength and incapable of reason with edge cases like creative writing for SciFi futurism. The alignment bleeds over. If you get on DDG and use the Anthropic Mixtral 8×7b, it is pretty good. The thing with models is to not talk to them like humans. Everything must be explicitly described. Humans make a lot of implied context in general where we assume people understand what we are talking about. Talking to an AI is like appearing in court before a judge; every word matters. The LLM is basically a reflection of all of human language too. If the majority of humans are wrong about something, so is the AI.

If you ask something simple like just a question, you're not going to get very far into what the model knows. Models have very limited scope of focus. If you do not build prompt momentum into the space by describing a lot of details, the scope of focus is large but the depth is shallow. The more you build up momentum by describing what you are asking in detail, the more it narrows the scope and deeper connections can be made.

It is hard to tell what a model really knows unless you can observe the perplexity output. This is more advanced, but the perplexity score for each generated token is how you infer that the model does not know something.

Search sucks because it is a monopoly. There are only 2 relevant web crawlers m$ and the goo. All search queries go through these either directly or indirectly. No search provider is deterministic any more. Your results are uniquely packaged to manipulate you. They are also obfuscated to block others from using them for training better or competitive models. Then there is the anti trust US government case and all of that which makes obfuscating one's market position to push people onto other platforms temporarily, their best path forward. - criminal manipulators are going to manipulate.

[-] thefartographer@lemm.ee 6 points 1 week ago

I asked Google why search engines are so bad now and its AI summaries its own deficiencies quite well:

Some say search engines have declined in quality due to a number of factors, including:

Search engine optimization (SEO) spam A wave of SEO spam has contributed to the decline in search result quality.

Affiliate marketing Affiliate link sites contribute to the low-quality content that floods the internet.

AI-generated content New technology can quickly produce low-quality content.

Marketing Search results are filled with marketing and links that may not be relevant to the query.

Recommender algorithms Some say the algorithm that recommends content is a mess. For example, someone might be recommended alt-right content after watching a click-bait video.

Ads Google's biggest business is advertising, and it's inserting more ads into its products to make more money.

Some say it's harder to find specific information these days, and that search operators are often needed to filter search results.

[-] vividspecter@lemm.ee 5 points 1 week ago* (last edited 1 week ago)

Perplexity seems to work but I don’t like the idea of AI giving me “facts” since they are mostly based on other AI posts

It helps that it gives actual sources, so you can verify them. But yeah, not helpful if all of the sources end up being AI posts.

[-] CkrnkFrnchMn@lemmy.ca 4 points 1 week ago

And here I thought Startpage was acting up...

[-] avieshek@lemmy.world 3 points 1 week ago
load more comments (1 replies)
[-] taiyang@lemmy.world 3 points 1 week ago

I wanted to make a joke about my first search engine, MetaCrawler, and then found out it's still around and still does search. Going down that rabbithole, it's changed hands a ton and was only relaunched kinda recently at some point. Is it any good? Nah, probably not.

I guess I'll just have to rely on my other aggregate search engine, SavvySearch (no, no the first search engine does not in fact still exist, much to my disappointment).

load more comments
view more: ‹ prev next ›
this post was submitted on 09 Oct 2024
608 points (96.6% liked)

Technology

58685 readers
4013 users here now

This is a most excellent place for technology news and articles.


Our Rules


  1. Follow the lemmy.world rules.
  2. Only tech related content.
  3. Be excellent to each another!
  4. Mod approved content bots can post up to 10 articles per day.
  5. Threads asking for personal tech support may be deleted.
  6. Politics threads may be removed.
  7. No memes allowed as posts, OK to post as comments.
  8. Only approved bots from the list below, to ask if your bot can be added please contact us.
  9. Check for duplicates before posting, duplicates may be removed

Approved Bots


founded 1 year ago
MODERATORS