Does any of these solutions work reliably for non-English languages? I’ve had a lot of issues trying to transcribe Swedish with all the products I’ve used so far.
Try ottex with Gemini 3 flash as a transcription model. I'm bilingual as well and frequently switch between languages - Gemini handles this perfectly and even the case when I speak two languages in one transcription.
I recall that early LLMs had the problem of not understanding the word "not", which became especially evident and problematic when tasked with summarizing text because the summary would then sometimes directly contradict the original text.
It seems that that problem hasn't really been "fixed", it's just been paved over. But I guess that's the ugly truth most people tend to forget/deny about LLMs: you can't "fix" them because there's not a line of code you can point to that causes a "bug", you can only retrain them and hope the problem goes away. In LLMs, every bug is a "heisenbug" (or should that be "murphybug", as in Murphy's Law?).
It doesn’t have to be, really. Even if it could replace 30% of documentation and SO scrounging, that’s pretty valuable. Especially since you can offload that and go take a coffee.
Yet no mention of the real friction: buying a domain and getting hosting set up. There are a number of free alternatives out there but they are not well known by the public.
There's certain level of friction to everything; that acts as a filter to separate those who choose to proceed anyway and those who don't. If you want to start painting, you have to buy a canvas, an easel, brushes, paint and set aside time to actually do it. Some people will abandon it because they like the concept of being someone who paints more than actually doing it. Some will proceed because they want to paint.
The same goes for website creation. You can post text, pictures and images on any social media site. The independent web is never going to be able to match that level of usability, and IMO it shouldn't try to. Part of the reason the indie web is interesting is because it's full of people who found their way towards wanting to build their own site.
Neocities is fairly well known and often listed in present-day personal website tutorials. Wordpress.com is also still there. Even if you get your own domain & hosting you usually have a nice web interface to drop the htmls into unlike in the old days when you had to FTP into the server and all that.
Manually writing html is more of a barrier than this. Back then there was a multitude of wysiwyg html editors like FrontPage, or Composer which was bundled with Netscape Navigator.
I wanted to spin up a mirror locally to do simple caching for docker builds but the tooling was lacking, there was a way to do a direct mirror of pypi locally but no other way of adding custom indices
I think Sonatype Nexus [1] can do that relatively easily. I don't know if the OSS version is enough, but I think most people and projects should be fine.
We've used Nexus OSS just the way you describe and it worked great.
We simply set it up as a kind of "passthrough cache", so if it didn't have the package it fetched it from pypi, and stored it to be used the next time someone wanted to install the same package.
Apart from being nice to pypi, we also got a bit of a decrease in CI runtime, because it fetched packages from the local cache 99% of the time.
I'll take a look, I think it is something I looked at and had some issues with but it has been a couple years and the only thing I can remember is bandersnatch
Pip already does its own caching, but it's maddeningly difficult to even locate and extract files, let alone set up anything usable. It's also needlessly difficult to make Pip just use such a cache directly - for example, if you haven't pinned a version, it will automatically check PyPI to figure out the latest version even if you have cached wheels already.
I don't know (I lack the experience), but I assume that container systems get in the way of Pip finding its normal cache, too. (If they're emulating a filesystem or something, then the cache is in the wrong filesystem unless you reuse the container.)
Visual iconography doesn't need to transmit the same ideas to different users, it's there to reduce space taken but still be identifiable to an experienced user of the tool.
reply