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.

DuckDuckGo is an easy first step. It’s free, publicly available, and familiar to anyone who is used to Google. Results are sourced largely from Bing, so there is second-hand rot, but IMHO there was a tipping point in 2023 where DDG’s results became generally more useful than Google’s or Bing’s. (That’s my personal experience; YMMV.) And they’re not putting half-assed AI implementations front and center (though they have some experimental features you can play with if you want).

If you want something AI-driven, Perplexity.ai is pretty good. Bing Chat is worth looking at, but last I checked it was still too hallucinatory to use for general search, and the UI is awful.

I’ve been using Kagi for a while now and I find its quick summaries (which are not displayed by default for web searches) much, much better than this. For example, here’s what Kagi’s “quick answer” feature gives me with this search term:

Room for improvement, sure, but it’s not hallucinating anything, and it cites its sources. That’s the bare minimum anyone should tolerate, and yet most of the stuff out there falls wayyyyy short.

“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.

[1] lori (@lori@hackers.town)

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.

Correct. This is also why Apple switched to zsh as the default shell over bash. They still ship Bash 3.2 in macOS, because from 4.0 on, Bash started using GPLv3 instead of GPLv2.

I’m not against the idea of creating proprietary software out of open-source software, if the license allows that. However, I am always against this practice of “closing the door behind you”.

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.

Bell Riots are coming this year. The Second American Civil War starts in 2026, which leads directly into WWIII.

From there, everything is pretty much terrible until warp drive is invented.

Oh, gotcha. I misunderstood and thought you were describing a Chrome-vs-Firefox difference specifically. Yeah, I can relate. I’m de-googling my life but I’m not sure I’ll ever be 100% de-googled. I’m taking it bit by bit. I sign up for new things with different email addresses now and occasionally I’ll change existing services if it’s possible. But there’s no way I’m going to go through my bajillion web site accounts and move them all.

I don’t understand the problem. Google services work in Firefox pretty much the same way, yeah? Does Chrome integrate an authenticator app? If som you might want change your 2FA settings at https://myaccount.google.com/security . If you have an Android phone you can get push notifications on it, or you can also use third-party authenticator apps.

It would be great if the frontend and backend were separated with a unified API and you could simply choose a frontend/interface (Vivaldi) with whatever backend/engine (Gecko). That’s not how it (currently) works though.

Arc has floated this idea. Currently Arc is Chromium-based, but they say they’ve designed it to allow for swapping engines in the future.

IIRC, Edge had a similar feature for a while, allowing you to run legacy Internet Explorer tabs if a site required it. Not sure if that still exists.

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.

Thank you for saving me the trouble of investigating this as an option.

No reason to tolerate proprietary licenses when there are so many viable FLOSS solutions out there.

I just checked to see if I missed a big update.

There’s still no Linux client, and it cannot sync files on Android (it only supports photo backups).

I can’t work around that limitation on Android with FolderSync, either, the way I can with Google Drive, Dropbox, Box, or any WebDAV- or S3-compatible server. Since it uses E2EE, any uploads need to go directly through the app, so integrations are difficult.

It doesn’t seem to have a search feature, either, at least not on Android. I can’t imagine there’s any content-aware search on the web UI, since that can’t be done server-side.

There’s been some interesting research in homomorphic encryption over the past couple years, which might someday lead to encrypted server-side search. But I think there are still major hurdles to actually implementing it securely and efficiently.

There are drawbacks to end-to-end encryption (E2EE). I’m not aware of any E2EE cloud storage systems that have the features Dropbox provides. I would LOVE to know of any that…

1. Support at least the big 5 platforms (Android/iOS/Mac/Windows/Linux).

2. Have a functional web interface.

3. Support sharing and collaboration.

4. Have a search feature

5. Sync to the local filesystem on a folder-by-folder or even file-by-file basis

6. Integrate with other tools (e.g. android file picker)

It’s not easy to do all that with E2EE, like a functional web interface, search, and integration.

ProtonMail’s search, for example, is limited to subject and metadata, and that’s specifically because they DON’T use E2EE for that.

I’m willing to compromise some of this for the sake of E2EE, but I’m not at all surprised that feature-first services are more popular than privacy-first services.

Sadly, there’s no official LineageOS for the OnePlus 10 or 11 series. I remember back with the 7 series it was officially supported on launch, and OnePlus sent units to open source developers. I don’t think OnePlus cares that much about the development community anymore.

https://wiki.lineageos.org/devices/#oneplus

I wish Apple followed these rules. So many deprecations in their man pages and developer documentation have no details at all. No idea what the supposed replacement is. No idea of the underlying reasons. No idea when it will cease to function.

This is why I still see “launchctl load” everywhere. It’s been deprecated for years, but the replacements are overcomplicated and not clearly communicated in official docs. When Apple finally pulls the plug, so much shit out there is going to break.

When they deprecated python2, they withheld implementation details and any timeline. Then they finally axed it in a freaking minor point release, without even replacing it with python3. AAAAAAH

This opens the door for more, as well. It means breaking the reliance on CUDA. Meta originally developed PyTorch and it’s still a large contributor. This means more resources will go into open backends instead of CUDA.

No no, you misunderstood. Everyone gave their explicit consent by clicking “agree” to the 80-page terms of service!

These are not “normal” tablets, but Boox’s line of ePaper-based readers are the only Android tablets that distinguish themselves sufficiently in my already-large family of devices. I’ve used “normal” tablets with full-color LCD/OLED displays, on both the Android and iPadOS side, but I rarely find a good use for them. I’ve found them to sit in an awkward space with neither the convenience of my phone, nor the utility of my laptop.

The ePaper-based tablets are ideal for reading, but I do not relegate them merely to the “e-reader” category because they allow you to install Google Play and run basically any Android app. This makes them more flexible and powerful than most e-readers.

It comes with a built-in browser optimized for monochrome, and you can also install third-party alternatives like EinkBro.

That said, it’s only for advanced users, and it’s not a perfectly smooth experience. Just getting Google Play running on it requires jumping through some hoops, and you will find that most Android apps simply don’t work well on a monochrome display (though Boox does offer color models, I have not used them myself).

I was hoping, for example, to use my Boox tablet to play Go, but despite the fact that Go is very much a “black and white” game, most of the apps use shading and colors that look like absolute ass on a black and white display. Some of them do not properly support the 4:3 aspect ratio either. So I don’t want to set unreasonable expectations here. These are niche devices.

Despite these drawbacks, I really appreciate having an ePaper device. It complements my device family (phone, laptop, etc.) in a way other tablets do not.