"Smart" may as well be synonymous with "unpredictable". I don't need my computer to be smart. I need it to be predictable, consistent, and undemanding.
I've been using Kagi for a while, so I'll post a few quick thoughts I had after reading the article, linked blog, and mastodon thread.
The one thing in the blog post I strongly disagree with is her statement that the summarizer is "the same old AI bullshit". I think they just assumed that without actually testing it. The summarizer is fantastic, and is a great example of the right way to use LLMs. Its output comes entirely from the URL or file you specify. It does not hallucinate. You can ask it follow-up questions about the document, and again, its replies are limited in scope to what's actually in that document. If you ask it something out of scope it'll tell you that it can't find that information in the document. This is great because it's using the LLM for what LLMs are actually good for — complex language parsing — and not for what they're bad for, like reasoning or information storage/retrieval. It's actually quite difficult to misuse the summarizer. It's straightforward and effective. This is Kagi's killer feature, IMO.
I can't speak as highly of its search-integrated AI features like FastGPT. They mostly take information from the contents of the first few search results, but they also seem to "fill in the blanks" more than I'd like. Sometimes it gives me information that is simply not in the sources that it cites. It's not as bad as using ChatGPT (which hallucinates all day every day, and if it ever tries to cite source is hallucinates those, too) but it needs improvement.
That said, Kagi doesn't shove the AI down your throat like you might think reading the blog post. These are separate features that need to be explicitly activated. Plain searches don't return results from the LLMs. If you want that, you need to explicitly go to the assistant or trigger the "quick answer" feature on the search results page. EDIT: I just realized that this is not totally true as of a few weeks ago, when they added a feature to automatically trigger the "quick answer" blurb for search queries ending in a question mark. Perhaps that's why Lori felt like it was over-emphasized.
Anyway, back to the summarizer, here is an example of it in action. I gave it the URL of the Mastodon post. I think this is an excellent result. I also asked it an unrelated followup question so you can see that it limits itself to the information in the URL. It will not make shit up!
The summarizer lets me download conversations in markdown form, so I'll just paste it right in here so you can see.
Exploring https://hackers.town/@lori/112255132348604770
Assistant:
Key points:
- The author wrote a blog post criticizing the search engine Kagi, which then prompted the CEO of Kagi, Vlad, to email the author directly to argue against the criticism. [1]
- The author woke up to an email from Vlad, the CEO of Kagi, who was upset about the blog post the author had written. [1]
- The author decided to publicly share the email exchange with Vlad, as they felt it was important for people to see his unhinged behavior. [1]
- The author refused to engage in a private debate with Vlad, as they did not want to be taken "to Crime Scene Number Two" without any accountability. [1]
- The author believes Vlad is unable to accept criticism or disagreement, and that it "eats him alive" when someone doesn't agree with him or his company. [1]
- The author states that no other search engine CEO has emailed them directly to "mansplain their company" in this manner. [1]
- The author sees Vlad's behavior as "petty and sad" and believes he has no understanding of boundaries. [1]
- Other users in the thread share similar experiences of Vlad's inability to accept criticism and his tendency to simply restate his own opinions rather than address counterpoints. [1]
- The author and others characterize Vlad's behavior as that of a narcissist who cannot tolerate disagreement. [1]
- The author and others are amazed by Vlad's decision to set up a separate company in another country just to print and give away t-shirts, rather than focus on improving Kagi's core search functionality.
Query:
What's the capital of North Dakota?
Assistant:
The knowledge provided does not contain any information about the capital of North Dakota. The context is focused on an email exchange between the author and the CEO of Kagi search engine regarding criticism of the company.
Personally, I have found this feature to be too limited. I still use the ClearURLs extension, which is more effective in my experience.
However, neither one is a silver bullet. Here's an example I just took from Amazon (I blocked out some values with X's):
Original URL:
https://www.amazon.com/Hydro-Flask-Around-Tumbler-Trillium/dp/B0C353845H/ref=XXXX?qid=XXXXXXXXXX&refinements=p_XXXXXXXXXXXXX&rps=1&s=sporting-goods&sr=XXX
Using Firefox's "copy link without site tracking" feature:
https://www.amazon.com/Hydro-Flask-Around-Tumbler-Trillium/dp/B0C353845H/ref=XXXX?qid=XXXXXXXXXX&refinements=p_XXXXXXXXXXXXX&rps=1&s=sporting-goods
Using ClearURLs:
https://www.amazon.com/Hydro-Flask-Around-Tumbler-Trillium/dp/B0C353845H?refinements=p_XXXXXXXXXXXXX&rps=1
The ideal, canonical URL, which no tools I'm familiar with will reliably generate:
https://www.amazon.com/dp/B0C353845H
Longer but still fully de-personalized URL:
https://www.amazon.com/Hydro-Flask-Around-Tumbler-Trillium/dp/B0C353845H
If anybody knows a better solution that works with a wide variety of sites, please share!
Apple: builds their entire software ecosystem on free, open-source foundations.
Also Apple: better have a million euros if you want to even start distributing software.
The best use case for an external app store is free open-source software, like we have on the Android side with F-Droid. Apple stopped that before it even started. Jeez.
Firefox syncs across devices as well, if you sign up for a Firefox account and enable sync. This works for bookmarks, logins, history, and you can even access remote tabs if you want. It's also easy to send a single page from one device to another.
On desktop, Firefox has an import feature that will pull your bookmarks and logins m other browsers (like Chrome) into your Firefox profile.
Even if you're neck-deep in Google services, Chrome doesn't do anything special.
A non-smartphone, that is, a cell phone like the ones that today’s parents had when we were young and with which we made calls and sent text messages, was enough for us, and it did not cause addiction.
That's not the way I remember it. Texting addiction was a thing. That's how Twitter became popular; it was basically a way to broadcast SMS to friends at first.
I guess it's a matter of degrees.
Ad-based services are the real problem here, I think. You don't hear people complaining about Wikipedia addiction.
Steve Wozniak, co-founder of Apple.
I don't think he was ever a billionaire, though he's certainly done quite well for himself. Since leaving Apple, he has founded several new companies and projects, focusing a lot on education and philanthropy. He was also involved in founding the EFF.
He's an engineer first and foremost, and several of his projects never achieved mainstream success, partly for being, IMHO, ahead of their time -- for example, a programmable universal remote in the 80s, and a GPS-based item tracker in the early 2000s.
As far as I know, he has never been involved in any notable scandals.
"no functional impact"? We clearly have very different ideas about the function of a display.
It's always something with Google, isn't it?
Has anyone else been able to reproduce this? I just tried and was not able to.
OP, is it possible these people were in group chats you were part of?
Nothing the linked blog post suggests Microsoft was "blindsided". Where did the Axios article get that "one minute" bit from?
Agreed. The time to push for third parties is every day except presidential election day. That's just the reality of the system right now.
Change doesn't begin at the top. It begins at the bottom. Many state and local elections across the US already use ranked choice voting, which is the bare minimum we would need to have more than 2 viable candidates in the presidential election. We need to push for ranked choice voting (or something better; it's not the be-all-end-all of voting systems!) in federal elections as well.
We have a generation of voters now who are literally too young to remember the 2000 election. If you're one of them, I urge you to look it up. I heard the same song back then. Look back and tell me if they were right or wrong, if you really believe that Gore would have been the same as Bush.
Don't let perfect be the enemy of good.
Is this legit? This is the first time I've heard of human neurons used for such a purpose. Kind of surprised that's legal. Instinctively, I feel like a "human brain organoid" is close enough to a human that you cannot wave away the potential for consciousness so easily. At what point does something like this deserve human rights?
I notice that the paper is published in Frontiers, the same journal that let the notorious AI-generated giant-rat-testicles image get published. They are not highly regarded in general.