Yeah it is pretty bizarre. On Android nowadays, when you click on some article that pops up as a notification, it takes you to Google and does an AI query to fetch you the article and then you see the content in Google.
Agree on google, Kagi though is usually better than ai responses. I’m actually a bit annoyed at the new Siri AI as it often does an AI response when I just want a Kagi search.
LLMs are a much better experience than what web search has become nowadays. And they probably are a better experience than what standard search could ever be.
But yeah, that doesn't mean they are doing much more than search.
The unwanted effect of AI overviews, in my experience, is turning their users into very-confidently-wrong arguers of everything.
The upside is that telling said users to double-check the sources usually results in them realizing the AI overview was wrong, but it's still a waste of everyone's time.
The 2021-era of of just "Not finding the results" was maybe a better outcome.
I get hallucinations every day, including ones where Google is mixing up three different similarly named products, or is telling me that I can mix two cleaning products (which would create chlorine gas). Tested today (2026-08-08).
Or a search for precise image downscaling in krita (on 2026-08-03) had the following Google AI result:
> To scale down an image in Krita by an exact integer factor with precise pixel sampling, use Scale Image to New Size or the Transform Tool, set your filter to Box, and input exact integer-divided values.
Except that that forum thread has the following posts:
> just use the "box" filter when scaling
Followed by
> There is no box filter.
Which is correct, as Krita does not have a box filter for scaling images.
It took two further rounds of back and forth for Google's AI (where it suggested nearest neighbor) to finish with
> You are entirely correct: Krita does not feature a true Box filter, and using Nearest Neighbor to downscale a complex image introduces heavy aliasing, skipped rows, and jagged artifacts.
This could've been avoided if the AI actually checked against the source code and documentation for krita, and checked the ingredients of the cleaning products in the other case together with basic principles of chemistry.
There's this saying:
> If one person says it's raining and another says it's sunny, a journalist is supposed to go out and look at the weather.
I don't need an automated way to summarize random half-truths from forum posts online. If AI is supposed to bring any benefit, it should be finding out the actual truth about the question being asked, not just report whatever opinions are being voiced online.
I remember years ago before LLMs my colleague told me he was impressed by my Google-fu. I was just as speechless whenever I saw him type his search queries which led nowhere. Apparently it’s a skill
Google search as become nothing more than a shitty AI by design. Alternative search engines are the only means to actually navigate.
I can still find core material using an alternative.
Don't worry, Google is now embedding that AI into Android's core. Rinse and repeat, expect the same results.
Yeah it is pretty bizarre. On Android nowadays, when you click on some article that pops up as a notification, it takes you to Google and does an AI query to fetch you the article and then you see the content in Google.
I hate it.
Sounds like a great way to inflate your success metrics for AI queries
Agree on google, Kagi though is usually better than ai responses. I’m actually a bit annoyed at the new Siri AI as it often does an AI response when I just want a Kagi search.
LLMs are a much better experience than what web search has become nowadays. And they probably are a better experience than what standard search could ever be.
But yeah, that doesn't mean they are doing much more than search.
Well I'm saying that asking Claude is a much better experience than the old Google search style of looking at 10 blue links.
They are doing more than search insofar as they are:
1. Reasoning about your question and trying to identify intent
2. Doing the search and accessing multiple search results for you
3. Formatting a response based on your intent and in the way you specify
This is collapsing many steps that humans used to have to do on their own. It's more ergonomic, and gets to a better answer, faster.
Google already has AI overviews which I use instead of polluting my ChatGPT, Claude, or Gemini chats.
The unwanted effect of AI overviews, in my experience, is turning their users into very-confidently-wrong arguers of everything.
The upside is that telling said users to double-check the sources usually results in them realizing the AI overview was wrong, but it's still a waste of everyone's time.
The 2021-era of of just "Not finding the results" was maybe a better outcome.
The difference is today it's mostly correct. I don't see hallucinations like a few years ago with AI generally, they know to use grounded search.
I get hallucinations every day, including ones where Google is mixing up three different similarly named products, or is telling me that I can mix two cleaning products (which would create chlorine gas). Tested today (2026-08-08).
Or a search for precise image downscaling in krita (on 2026-08-03) had the following Google AI result:
> To scale down an image in Krita by an exact integer factor with precise pixel sampling, use Scale Image to New Size or the Transform Tool, set your filter to Box, and input exact integer-divided values.
With the source https://forum.kde.org/viewtopic.php%3Ff=274&t=135270.html
Except that that forum thread has the following posts:
> just use the "box" filter when scaling
Followed by
> There is no box filter.
Which is correct, as Krita does not have a box filter for scaling images.
It took two further rounds of back and forth for Google's AI (where it suggested nearest neighbor) to finish with
> You are entirely correct: Krita does not feature a true Box filter, and using Nearest Neighbor to downscale a complex image introduces heavy aliasing, skipped rows, and jagged artifacts.
This could've been avoided if the AI actually checked against the source code and documentation for krita, and checked the ingredients of the cleaning products in the other case together with basic principles of chemistry.
There's this saying:
> If one person says it's raining and another says it's sunny, a journalist is supposed to go out and look at the weather.
I don't need an automated way to summarize random half-truths from forum posts online. If AI is supposed to bring any benefit, it should be finding out the actual truth about the question being asked, not just report whatever opinions are being voiced online.
What are your actual prompts? And what model are you using?
I remember years ago before LLMs my colleague told me he was impressed by my Google-fu. I was just as speechless whenever I saw him type his search queries which led nowhere. Apparently it’s a skill
Until they inevitably shit it up. To be apples to apples, gotta compare to peak google era