61–70 of 187 posts
Honestly, I use Edge Copilot for almost all my searches now. Google is no longer looking and soon the majority of people will realize that.
Earlier quoted context omitted.
Kagi costs Spotify money, has zero ads, and lets you customise the results.
It also can't fetch more than 2 pages of results for either web or image search. Reverse image search just straight up doesn't work. I don't know why they have it. With searxng, searching at least works. It also has plugins that I think can do some of what Kagi is useful for (but it depends on the instance)
I can't speak for image searching, but I found when I get limited results from Kagi, The other search engines that produce More results just pad those results with noise. Sometimes I'll do a specific search and have no results on Kagi, so I switched to another engine justified I have thousands of unrelated results
Earlier quoted context omitted.
> No ads, no nonsense, just the answer. 5 - 10% of the time that answer will be complete rubbish. We need something better than Google and LLMs e.g. Golden before it was acquired: https://golden.com
Kagi works great.
3rd organic link is a 404. And the rest of the links are either not timely e.g. from 2016 or niche e.g. for Telehealth.
Also it is not location aware so mention of Bestbuy even when not from US.
Earlier quoted context omitted.
This was inevitable. Traditional search is an inefficient way to access information in a world with large AI models. Google is being forced to do this due to competition from openAI, meta.ai, perplexity, etc.
LLMs cannot compete on truthful high-quality information from experts. Only on plausible babble. If that’s the only information you search for, then your perspective makes sense. We shouldn’t be using LLMs for information retrieval at all. They should be summarizing individual web pages at best. That would make search more efficient. But to use plausible text generator without any guaranteed veracity checks in the pi…
The article starts with intimating that SEO is the problem. Perhaps to an extent it is, though I'd say with G's massive market share that optimising for one sweet spot with one search engine is really the problem. It makes SEO easier, one search engine and criteria. 20-25 years ago when there were half a dozen prominent engines you'd be ranking well in some but not others. A good argument for alternative algorithms (…
>20-25 years ago when there were half a dozen prominent engines That's not how I remember it. My recollection is that for a year or 2 (roughly 1998 and 1999) Altavista was the dominant engine, which rapidly gave way to Google essentially as soon as Google became available, and since 2000 Google has been the dominant engine. In the late 1990s and early 2000s, I was getting my info on what engines people were using mos…
I searched for how to use a massage ball (my back hurts) last week and got a giant page full of ads and ad-like sections for buying one with barely any articles at all. That is not a search engine; it's an ads engine.
I tried again in the local language and now I see some product ad results for buying a massage ball, but then it's back to the video results and sports blogs showing how to use them. That seems OK. Probably most people searching for massage balls do want to buy one or are very likely to do so soon.
I dunno, seems like they're both pretty good pages of results.
We need to make bookmarks a common way to access the web again! So many people use Google or other search engines to access even the most basic sites, instead of storing a bookmark or typing out the whole URL. I have used a simple bookmarking strategy in Firefox for some years now, simply storing everything and anything I suspect I might want to retrieve later. I give each bookmark a few quick keywords and store it a…
I searched for how to use a massage ball (my back hurts) last week and got a giant page full of ads and ad-like sections for buying one with barely any articles at all. That is not a search engine; it's an ads engine.