[-] hersh@literature.cafe 2 points 14 hours ago

That's pretty much what I do, yeah. On my computer or phone, I split an epub into individual text files for each chapter using pandoc (or similar tools). Then after I read each chapter, I upload it into my summarizer, and perhaps ask some pointed questions.

It's important to use a tool that stays confined to the context of the provided file. My first test when trying such a tool is to ask it a general-knowledge question that's not related to the file. The correct answer is something along the lines of "the text does not provide that information", not an answer that it pulled out of thin air (whether it's correct or not).

[-] hersh@literature.cafe 2 points 14 hours ago

I get that, and it's good to be cautious. You certainly need to be careful with what you take from it. For my use cases, I don't rely on "reasoning" or "knowledge" in the LLM, because they're very bad at that. But they're very good at processing grammar and syntax and they have excellent vocabularies.

Instead of thinking of it as a person, I think of it as the world's greatest rubber duck.

[-] hersh@literature.cafe 4 points 1 day ago

It's as open as most Android brands. I don't use any of Boox's services or apps. I installed F-Droid and use open-source apps from there. I use Librera as my ebook reader, with Syncthing to sync my book library between my desktop, ereader, and phone. It's possible to set up the Play Store but I don't bother, personally.

It's not a 100% smooth experience but I'm very happy with the F-Droid compatibility. I absolutely refuse to get locked into a walled garden.

[-] hersh@literature.cafe 3 points 1 day ago

I've done this to give myself something akin to Cliff's Notes, to review each chapter after I read it. I find it extremely useful, particularly for more difficult reads. Reading philosophy texts that were written a hundred years ago and haphazardly translated 75 years ago can be a challenge.

That said, I have not tried to build this directly into my ereader and I haven't used Boox's specific service. But the concept has clear and tested value.

I would be interested to see how it summarizes historical texts about these topics. I don't need facts (much less opinions) baked into the LLM. Facts should come from the user-provided source material alone. Anything else would severely hamper its usefulness.

[-] hersh@literature.cafe 2 points 4 days ago

Related feature on my wish list: I'd love a way to basically fork a feed based on regex pattern matching. This would be useful for some premium feeds that lump multiple podcasts together. For example, one of my Patreon feeds includes three shows: the ad-free main feed, the first-tier weekly premium feed, and the second-tier monthly premium feed.

I don't want to filter them out because I DO want to listen to all of them, but for organizational purposes I don't want them lumped together. I'd prefer to display these as two or three separate podcasts in my display.

Another example is the Maximum Fun premium BoCo feed. They include the bonus content for ALL their shows (which is...a lot) in a single feed. I only listen to about half a dozen, and even that is a bit of a mess in one feed!

[-] hersh@literature.cafe 59 points 6 months ago

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.

41
submitted 7 months ago by hersh@literature.cafe to c/linux@lemmy.ml

I looked this up before buying the GPU, and I read that it should "just work" on Debian stable (Bookworm, 12). Well, it doesn't "just work" for me. :(

clinfo returns two fatal errors:

fatal error: cannot open file '/usr/lib/clc/gfx1100-amdgcn-mesa-mesa3d.bc': No such file or directory

fatal error: cannot open file '/usr/lib/clc/gfx1030-amdgcn-mesa-mesa3d.bc': No such file or directory

I get similar errors when trying to run OpenCL-based programs.

I'm running a backported kernel, 6.6.13, and the latest Bookworm-supported mesa-opencl-icd, 22.3.6. From what I've found online, this should work, though Mesa 23.x is recommended. Is it safe/sane to install Mesa from Debian Trixie (testing)?

I've also seen references to AMD's official proprietary drivers. They do not officially support Debian, but can/should I run the Ubuntu installer anyway?

I'm hoping to get this up and running without any drastic measures like distro hopping. That said, if "upgrade to Testing or Unstable" is the simplest approach, I am willing to entertain the idea.

Thanks in advance for any help you can offer.

[-] hersh@literature.cafe 61 points 7 months ago

"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.

[-] hersh@literature.cafe 63 points 8 months ago* (last edited 8 months ago)

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.

[-] hersh@literature.cafe 59 points 10 months ago

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!

[-] hersh@literature.cafe 227 points 11 months ago

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.

[-] hersh@literature.cafe 71 points 1 year ago

"no functional impact"? We clearly have very different ideas about the function of a display.

It's always something with Google, isn't it?

[-] hersh@literature.cafe 46 points 1 year ago

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?

view more: next ›

hersh

joined 1 year ago