My workflow (return on success):

1. DDG

2. Google

3. Whichever LLM is closest at hand

4. This is information the world was not meant to know

I used to use Google as a fallback from DDG. I haven't had to do that in a long time; now, the only time I use Google is for the specific answer "what does Google return for this".

The only thing I use Google for anymore is reverse image search.

Brave Search is actually better than DDG these days. Kagi is supreme though

(Also Marginalia for deep search)

Isn't Kagi basically Brave search?

No? Different features, different indices, Brave Search is free/ad supported. https://help.kagi.com/kagi/why-kagi/kagi-vs-brave.html

First time I heard about Marginalia, I'll check it out.

> I know many people are increasingly frustrated with Google

I’m not sure if this holds true nowadays. I’d say it git pretty bad, but now Gemini summary pretty much covers all of my use cases. And for any meaningful query, it’s straight to ChatGPT/Claude.

[delayed]

Very rare for me to use Google nowadays for something niche. For those cases, I would assume it requires multiple sources to get a definitive answer, so it goes to ChatGPT.

[delayed]

Why do you think there’s a high error rate for general queries nowadays?

[delayed]

Yeah fair. I guess I have a very different experience, as I mentioned above, I basically never use it for any niche/hard queries that depend on multiple sources or research. For all my common queries, it's reliable.

[delayed]

Sorry, not going to take the bait here. I would argue in 2024/2025 it was dogshit, but it really isn’t nowadays. You can even see the sources for most of the summary queries, like literally on the same line as the bullet point.

My google queries are like different combos of weather, specific event questions, directly attributed to wikipedia data and etc. LLMs are way past the point of reliability when it comes to data extraction from static websites.

> LLMs are way past the point of reliability when it comes to data extraction from static websites.

Two very modern counterexamples:

https://app.opencve.io/cve/CVE-2026-83844

https://www.sentinelone.com/vulnerability-database/cve-2026-...

The information they feed from is simple, clear, and static. And yet the both of them are hallucinating mitigations, compromise indicators, and other details of the vector that flatly don't exist.

The question GP posed wasn't bait. It's still a blatant problem in 2026. It's not just shitty cheap models, either. Just this morning I caught 6.1 Sol (via Codex) incorrectly answering a question about the codebase it was actively working in.

That is fair. I always ask for sources whenever it is something I am unfamiliar with instead of just trusting the response, that way I can go and double check and it ensures the agent at least read something on the topic

I've found the value of this approach has diminished over time - now I need to go and read the source and try to identify if it was generated by an LLM itself.

> And for any meaningful query, it’s straight to ChatGPT/Claude.

What a disgusting use of technology. Kicking a query to an agent, that's leveraging a model that has bulk of humanities information in it, so it can use a web browser to go looking for the thing you searched. WTF.

As opposed to Googling, which will

1. leverage the AI Overview model (with the IQ of a brain-damaged monkey),

2. run an ad auction and populate the first 6-10 items from that,

3. then do a perfunctory exercise of searching its spam-riddled index to round out a few results at the very bottom of the page.

Yeah, that guy asking ChatGPT is a monster.

You forgot to mention all the well-documented ad auction fraud that came out during the anti-trust trial (they defraud advertisers and sites and do some shady stuff to users —- on every impression).

Yeah! Reading stuff written by people sucks!

I never said that? But when i’n searching for a certain answer, I don’t really care about paragraphs, posts, etc. A good chunk of time it might be data auto-generated from big databases too.

Time and place for every tech/use case. When I’m in the mood for reading long pieces, i do that deliberately.

I actually like to discover some lost articles that I vividly remember and it's honestly great for that.

Just use a decent search engine dummy.

What a dumb reply

Dumber than I'm so stupid I'd rather read llm generated garbage that massages my ego... What an insightful question, you're really thinking about this the right way!

Why am I not surprised by that reply.

Because you are an idiot

We've banned this account for repeatedly breaking the site guidelines and ignoring our requests to stop.

If you don't want to be banned, you're welcome to email [email protected] and give us reason to believe that you'll follow the rules in the future. They're here: https://news.ycombinator.com/newsguidelines.html.

We've banned this account for repeatedly breaking the site guidelines and ignoring our requests to stop.

If you don't want to be banned, you're welcome to email [email protected] and give us reason to believe that you'll follow the rules in the future. They're here: https://news.ycombinator.com/newsguidelines.html.

We detached this subthread from https://news.ycombinator.com/item?id=50385425.

Except the summary doesn't fucking work. It's consistently wrong.

As I mentioned above, if you’re making a niche query, maybe. If you’re making a very generic query “average temperature in Hong Kong in January”, it’s fine. You’re overestimating average complexity of a query.

"Fine" may be "right 95% of the time" but I'll look like a jackass 5% of the time that I trust the Google AI Overview.

And I won't know which ones are the wrong ones, so I may as well trust it 0% of the time.

Most people I know use AI Overview now as their primary way of doing any sort of research or question-answering... and I urge them: If getting an LLM take is suitable for your purpose, at least ask free-tier ChatGPT, which is at least an order of magnitude less likely to vomit up false or confused information. Also, asking actual Gemini is another sane option that is far superior to AI Overview.

Does it really matter that much? Did it matter that everyone's parents pre-internet were wrong half of the time?

Most people are not asking google to build them a train signaling system but to look up some question on Wikipedia for which the answer does not matter that much

If that’s the case, those people should just install a 7M param model on their phones and use that. It’s probably as accurate, but works offline.

Sure but that is harder than pressing a button or saying hey Google. It requires you to think, make a UI, etc.

Think of the incentives and the path of absolute least resistance/thinking/energy use and you will arrive at the product people want.

I think you can press a button + say "Hey Siri" at this point (though that assumes Siri works at all, which I agree is a stretch.)

7M param doesn’t do web searches for you. Otherwise, yeah?

7M is fine if you don't care about the quality/correctness of the output and just want some utterance that looks plausibly related to the question. I guess that is the bar this thread has set for Google search quality being good enough for most users.

> Does it really matter that much?

Does truth matter in the post-truth world where disclaiming truthful news about you is as easy as calling it fake?

Interesting, I had terrible experience with ChatGPT as search not-so while back, found gemini quite useful for finding out the articles and brainstorming information.

> but now Gemini summary pretty much covers all of my use cases. And for any meaningful query, it’s straight to ChatGPT/Claude.

How do you live like this?

I use it much less than I did prior to LLM becoming useful. However, when I need to search, it just works. Their AI integration with their search is also great, but I couldn't justify it and ChatGPT subscription. I can't bring myself to cancel Kagi entirely, though. I still did 600 searches this month.

It's a AI answer and a huge page of ads

For me, it took 30-60 seconds to notice dark mode preferences on my browser, but popped up an ad saying that search is garbage without the app, and that I should install their malware on my phone.

When I dismissed the popup, it produced much better results than screenshots I’ve seen from logged in browsers.

I guess that’s an improvement?

Yeah, agreed. If Claude/ChatGPT would load and respond faster, i’d go for them. But Google’s speed is unmatched for quick queries.

Every time I get a Gemini summary it reminds me not to use google. It's almost always wrong about key data.

Try Kagi. Honestly. It craps on DDG.

A few months ago I stopped paying for kagi and went back to DDG. I started noticing all the top results were AI generated, so I just went back to Kagi yesterday and it is a huge breath of fresh air. So much better!

I pay for kagi, but hardly ever use search any more.

Come to think of it, one of my boxes is not logged into kagi, and is mostly ai nonsense.

I guess I’ll keep paying them. :-)

"Top results" was the complaint, this hides AI coming from Duck but not from Duck's results.

I did something similar, when the Kagi Translate changes were announced earlier in the year. I tried a local hosted AI assistant (via openrouter) along with DDG/Brave.

80% of the time the search results were perfectly fine, but that small amount of time would royally annoy me and my breaking point was this: https://i.redd.it/r4q6y3vl5vdh1.png

So I went back to Kagi and appreciate it a little more (they've also rolled back on Translate to some degree).

As far as data goes, Kagi often lags behind Google. It will return outdated or irrelevant articles quite often.

However, Google has shat the bed, itself, the room the bed is in, the neighbors and half of the city with the search. Since search no longer returns any semblance of relevant data, but ads and wrong AI summaries.

So for vast majority of use cases I find Kagi much more superior. And in 1 or 2 cases when I'm frustrated with the results I can append `g!` before the query to get the shitty Google results.

The only downside: Apple doesn't let you set a custom search engine to Kagi. And (a very unpleasant surprise for me) neither does Firefox. You need extensions.

I am waiting for someone at Apple[1] to explain why I can't set any arbitrary site as my search provider on mobile on the phone that I paid for.

(Does Chrome on mobile allow it? I use Edge on iOS which also only has a hardcoded list, so while I don't know for sure, but I assume not)

[1] no doubt i will be waiting until i am dead

I'm guessing that apple wants to get paid for placement in the preferred search provider listing.

[delayed]

Yes Firefox does, you just need to visit it once and it's in the list. You can also add it manually if you want. I used it that way both on desktop and android.

My mind managed to completely blank out and not even see the "Add search engine" button in settings :D

DuckDuckGo has never had good search results.

It's mostly Bing

It’s been statistically indistinguishable or better than Google for at least a decade.

Google intentionally serves bad results now to juice ad impressions (according to sworn testimony from their execs), so I assume DDG is significantly better these days.

I tried to switch to DDG multiple times within the last decade and it was very clearly worse than Google even as Google declined. There would be zero relevant results on page 1, I switch to Google, plenty of relevant results. This happened every single day.

I have literally never had that experience with any of the following search engines:

- DDG

- Kagi

- Bing (10+ years ago)

- Yahoo (I'm getting old...)

I searched by typing lists of keywords into the search box in the past. Maybe you're one of those people that types sentences, or relies heavily on synonym matching? (Which finally works now, but only if you turn on LLM mode -- even then, Google shipped that months or years after kagi, and the reviews are scathing vs. the performance I get out of the Kagi AI search.)

>Google intentionally serves bad results now to juice ad impressions (according to sworn testimony from their execs)

[Citation Needed]

Kagi is awesome, it's what Google used to be. I tried to switch to DDG, but I found that I had to use the !g option more often than not to get good results. With Kagi, I've never had to do that.

Tried them all. When looking for obscure sites, I still find Google to be the best above all. DDG will often miss results, Kagi and Brave will be better but still not have the vast amount of sites indexed like Google does. Also, I'm still surprised to this day that searching "duckdns" on DuckDuckGo doesn't bring up the DuckDNS site -- maybe they have something against other ducks?

As for Google, I typically only use its "Web" search so I skip all the junk Google adds to the `All` tab. With Firefox or Chrome, you can make a custom search engine with `&udm=14` appended, like `https://www.google.com/search?q=%s&udm=14` if you want it to be your default search engine.

I think Kagi more aggressively blocks garbage, which is probably the tradeoff you are seeing.

The last time kagi failed me, I flipped on claude research mode. It found a microfiche archive, OCR’ed it, then started retro-stalking obscure 90’s celebrities (read old interviews, found coworkers, etc).

It took 15 minutes, but it produced an accurate 20-30 page report, then converted it to machine readable form for downstream use. I tried doing the same research myself a few years ago and failed to find anything at all.

As the kids say: Google’s cooked.

N+1 I have paid for Kagi for a couple of years. I describe it as google search back when google search was actually useful.