Skip Navigation

InitialsDiceBearhttps://github.com/dicebear/dicebearhttps://creativecommons.org/publicdomain/zero/1.0/„Initials” (https://github.com/dicebear/dicebear) by „DiceBear”, licensed under „CC0 1.0” (https://creativecommons.org/publicdomain/zero/1.0/)U
Posts
2
Comments
32
Joined
3 yr. ago

  • I used to have this issue more often as well. I've had good results recently by **not ** pointing out mistakes in replies, but by going back to the message before GPT's response and saying "do not include y."

  • Yes. I believe the paid version only gives you more possible nodes (where the transcoding is done), and more reports? But yes, you have the entire suite of tools necessary in the free version. It's worked great for me, I've used it for a year and a half now

  • Agreed. I've converted my library all to 265 using Tdarr, I'm up to 11.5 TB of saved space. I like having all my media be uniform for my Plex server, and Tdarr is a nice and easy tool to achieve it

  • FMD2 (for auto-downloading manga), Komga (for hosting manga on a local server), and Tachiyomi for a self-hosted solution, if you're interested.

  • I suppose the issue here is more semantics than anything, yeah. I think better discussion would be had if the topic was "how can we help LLMs better understand and present information," as opposed to a more sensational "GPT will cheat and lie"

  • I think the reason I'm not comfortable with using the term "lying" is because it implies some sort of negative connotation. When you say that someone lies, it comes with an understanding that they made a choice to lie, usually with ill intent. I agree, we don't need to get into a philosophical discussion on choice and free will. But I think saying something like "GPT lies" is a bit irresponsible for the purposes of a discussion

  • They said "it just repeats words that simulate human responses," and I'd say that concisely answers your question.

    Antropomorphizing inanimate objects and machines is fine for offering a rough explanation of what is happening, but when you're trying to critically evaluate something, you probably want to offer a more rigid understanding.

    In this case, it might be fair to tell a child that the AI is lying to us, and that it's wrong. But if you want a more serious discussion on what GPT is doing, you're going to have to drop the simple explanation. You can't ascribe ethics to what GPT is doing here. Lying is an ethical decision, one that GPT doesn't make.

  • The best I've found is Free Manga Downloader 2 (https://github.com/dazedcat19/FMD2). It's not perfect, I have some gripes, but I have FMD2, mylar3, komga, and Tachiyomi (on my mobile devices) with the kogma extension for all my comic stuff. Works well enough for me

  • Would love to deploy this, but unfortunately I'm running older server equipment that apparently doesn't support MongoDB 5 (Error message MongoDB 5.0+ requires a CPU with AVX support, and your current system does not appear to have that!). Tried deploying with both 4.4.18 and 4.4.6 and can't get it to work. If anybody has some recommendations, I'd appreciate hearing them!

  • That's what I've been seeing, but I run enough stuff on Windows that has poor support for Linux that makes it a toss-up. Do you think it's feasible to run Docker on Linux in a Hyper-V container on Windows? I'm really trying to evaluate my options, I've considered Proxmox to separate my Windows and Linux stuff; currently I am running an instance of Ubuntu in Hyper-V for my Linux stuff. Do you think Proxmox is more viable?

  • Brought to you by the space pope