• 0 Posts
  • 13 Comments
Joined 1 year ago
cake
Cake day: September 27th, 2023

help-circle
  • I posted some of my experience with Kagi’s LLM features a few months ago here: https://literature.cafe/comment/6674957 . TL;DR: the summarizer and document discussion is fantastic, because it does not hallucinate. The search integration is as good as anyone else’s, but still nothing to write home about.

    The Kagi assistant isn’t new, by the way; I’ve been using it for almost a year now. It’s now out of beta and has an improved UI, but the core functionality seems mostly the same.

    As far as actual search goes, I don’t find it especially useful. It’s better than Bing Chat or whatever they call it now because it hallucinates less, but the core concept still needs work. It basically takes a few search results and feeds them into the LLM for a summary. That’s not useless, but it’s certainly not a game-changer. I typically want to check its references anyway, so it doesn’t really save me time in practice.

    Kagi’s search is primarily not LLM-based and I still find the results and features to be worth the price, after being increasingly frustrated with Google’s decay in recent years. I subscribed to the “Ultimate” Kagi plan specifically because I wanted access to all the premium language models, since subscribing to either ChatGPT or Claude would cost about the same as Kagi, while Kagi gives me access to both (plus Mistral and Gemini). So if you’re interested in playing around with the latest premium models, I still think Kagi’s Ultimate plan is a good deal.

    That said, I’ve been disappointed with the development of LLMs this year across the board, and I’m not convinced any of them are worth the money at this point. This isn’t so much a problem with Kagi as it is with all the LLM vendors. The models have gotten significantly worse for my use cases compared to last year, and I don’t quite understand why; I guess they are optimizing for benchmarks that simply don’t align with my needs. I had great success getting zsh or Python one-liners last year, for example, whereas now it always seems to give me wrong or incomplete answers.

    My biggest piece of advice when dealing with any LLM-based tools, including Kagi’s, is: don’t use it for anything you’re not able to validate and correct on your own. It’s just a time-saver, not a substitute for your own skills and knowledge.




  • Because it’s not the same class of device. The PS Portal is very niche. It’s a $200 device that basically just runs the PS Remote Play app.

    I’ve used PS Remote Play on my phone and laptop, and it’s just not good in the cases I actually want to use it: when traveling away from home. Even with a good Internet connection it’s only “okay”. It’s utterly useless when in transit (trains, places, etc.), and 99% useless in any public place (e.g. cafe or library WiFi).

    These are all cases where the Switch, Deck, and similar devices excel. The PS Portal addresses a much smaller market.




  • I doubt any billionaires have that much money “sitting in a bank”.

    Most wealth is non-liquid. For example, if you found a company that becomes massive, and you maintain a controlling share, then you could be a billionaire on paper while having no real money to spend – the only way to turn that into “real” money would be to sell shares in the company, and thus lose control of it. If the company is doing good work, it could be better to retain control and act through the company, by ensuring that it pays employees good wages to do good work for the benefit of society. This is not completely incompatible with profit in theory, though in practice…yeah. I’m not sure if there are any such billionaires in the world today.

    The real problem is more fundamental to the economy, in that it fairly consistently rewards bad behavior.

    Larry Page basically became a billionaire overnight when Google went public. I don’t recall Page or Google doing anything especially evil or exploitative before that, though their success was certainly built in an unsustainable economic bubble.

    If Amazon didn’t treat its employees like shit and poison the entire economy, then Bezos could probably still be a billionaire and I wouldn’t necessarily hold that against him.


  • 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.




  • I would advise against any rolling distro if you use Nvidia drivers and CUDA. When I was using Tumbleweed it kept breaking with kernel updates. This was common in the forums. I had to pin my kernel to an older version to fix it. It was not ideal.

    I’ve come full circle back to Debian stable. I’m sure at some point I’ll need a newer package and be frustrated again. When the time comes, perhaps I’ll try distrobox if I can’t easily backport it.


  • The github page has more context than the F-Droid listing.

    API Key

    This application uses the AudD® service as a Music Recognition API. You need a special API token provided by AudD® to use the application. If you don’t have one, you can sign up for a free API token. You can add the key on the onboarding or preferences screen, or just set it in local.properties.

    There is also the option to use the app without a token, but please note that this will restrict the number of daily recognitions that can be performed.

    The AudD web site says:

    Music recognition API for both content analysis and in-app music recognition costs from $2 to $5 per 1000 requests. First 300 requests for free.


  • I feel this.

    Back in the 90s, there was a fantastic paint program for Mac called ColorIt! (The exclamation point is part of the name, though this is the last time I will respect that because it’s obnoxious; lookin’ at you, Yahoo!*)

    It was a commercial product, but ColorIt 2.3 was eventually released as freeware after newer major versions were released for sale. 2.3 was everything I needed, and while I did try ColorIt 4.0, it didn’t click with me the way 2.3 did. At the time I felt like they bowed to the pressure of Adobe’s success and instead of playing to their unique strengths, they made ColorIt’s UI a bit too much like Photoshop. So I stuck with version 2.3.

    By the time Mac OS X came around, ColorIt was no longer in active development. But OS X had the “Classic” environment, something akin to an OS 9 VM tightly integrated into OS X. Classic apps didn’t look or feel like native OS X apps, and running Classic came with a heavy RAM burden. But I did it anyway, because ColorIt 2.3 was da bomb.

    I continued using ColorIt 2.3 up until Apple killed support for Classic in 10.6 Snow Leopard.

    At that point, the intrepid developers came out of hiding and created a Carbon port of ColorIt 4.5 that could run natively on OS X. It was Carbon-only, which meant that it it didn’t run natively on Intel Macs, but it did run thanks to Apple’s Rosetta compatibility layer — at least until Apple axed that as well.

    If I ever get into pixel art again, I’ll probably run ColorIt 2.3 again in an OS 9 VM with Sheepshaver or whatever works best nowadays.

    *That exclamation point is strictly to emphasize my disdain for Yahoo.