enthusiasm_headquarters @ enthusiasm_headquarters @lemmy.world

I just want AI to be my buddy

---

Read more

Posts

3

Comments

80

Joined

12 mo. ago

Thank you for the reply. I'm a bit less knowledgeable on these tools you've mentioned. Forgive my ignorance, but what is meant by a witchcraft hack?

Also not sure what I've done to deserve downvotes... Peculiar. Anyways, the "unsigned" and "no signature" advice was quite good. I don't mind simply incorporating negative prompts into prompts; it's a bit more intuitive-- why are there two queues for rendering anyways? I don't order a cheeseburger from a diner twice, one order with everything I want, the other order with everything I don't want (NO ANIME CHEESE, NOT RAW, NOT SMASHED)...

By the by I'm seeing a lot of blatant "Artstation" watermarks and imprintings as well in my results, without requesting this. Maybe the presets should be tweaked to fix this problem.

Ah well. Here's to hoping. Thanks for the reply.

GPT is terrible at consistent memory. It won't know what to focus on unless you constantly tell it. There are a few tricks to make it better.

1. You can type /mem and get a list of what its memorizing, assuming you have memories enabled. This can allow you to remove garbage that the AI fixates upon. This can be a good source of lore as well if you don't feel like writing it.
2. The stuff in the character description is very important, it's always referring to it seemingly more than any other source.
3. I can't tell how effective adding lore to the lore URL field in the character settings really is. I honestly have no idea if it works. When I click on reply details from the AI is never actually says it has used my lore files, so I have no idea. But it's something to try.
4. Sometimes the reminder function actually works as intended. Sometimes.
5. Dev has stated that the text model is messed up and outdated. They said April would be a release date for a new version of the text AI model, but I didn't believe it because it's a big change. I'm not upset about it, I imagine upgrading this beast will take some time.

Trump sort of sounds like vomit getting caught in your throat after a burp, the Musk is what comes out when you finally hurl.

Yeah if you fiddle around with about:config without knowing exactly what yer doing, shit breaks. Fortunately you can type "about:profiles" in the url box, make a test profile, and mess around as much as you want before nuking your default browser.

I read about this too, and it worries me. Google has donated over a billion dollars to Mozilla over the years. That alone doesn't scare me so much as it's a blatant propaganda tool to deflect the antitrust sentiment that plagues them and will probably some day do its work of breaking them apart.

Fortunately, there are numerous open source forks. I am currently using Librewolf, a fork of firefox focused on privacy and anti-tracking, and it has worked without a hitch. A couple of my extensions have required fiddling with to get right but it's part of life if you care about these things.

NordVPN was found selling user data years ago and it's dubious that they even provide real VPN services, as they are not open source. They are part of a large conglomerate of corporate VPNs and shouldn't be trusted. It's a shame so many social media influencers accept their money from promotions.

I use Airvpn, a non-profit run by hacktivists out of Italy and have been for years. I have not been having technical problems with perchance tools due to VPN, though I am not permitted to join chat boards or start an account on perchance while on my vpn. Kind of a shame but I can live with it.

I will always have some admiration for a person that sets up shop in Microsoft's back yard and bases the system on Linux. I hate the DRM aspect and couldn't care less about what promoting whatever with children because quite frankly that's just not going to be solved by anything other than parents taking better care of their kids. The same can be said about exposure to any kind of media, including not letting children watch commercials on Saturday morning because gee whiz, that stuff is exploitative.

To me complaints about exposing kids to gambling is just finding something to be pissed off about and reinforces my feeling that the Left has picked up the kinds of puritanism that used to be associated with the Right.

But yeah. DRM software is a serious thing to worry about. Selling people vapor is kind of a shitty thing to do.

While I wasn’t a mod for Steam proper, I was a mod for a popular game that routinely had its share of hate groups and 8ch mobs try to take over. The flagging system worked pretty well for keeping the worst of this stuff out. Plus, the publisher is permitted to make moderators for its own Steam forum. So if you are seeing shit get out of hand on a particular title, blame the publisher, not Steam.

NordVPN not a true VPN. They got in trouble some years back for leaking (or selling) user data. Use protonvpn, airvpn, or mullvad. :)

dot-producting the arrays

It took me a while to figure out that the AI does not understand how to match pronoun with its subject. Too-many-fingers aberrations would happen in the text where character genders would suddenly morph or they would transport magically to replace the actions of another person. It's kind of an annoying problem.

I’ve noticed this too. It also uses the same turns of phrase across many characters, which makes me think the conversational training data is somewhat limited. One thing you can do is a “nuclear” option. I was testing the Strict GM default character on a sci-fi adventure, and the AI became obsessed with putting my party in these crystal caves.

Everything became about the caves. The caves would start to feel my words and resonate with all the action. I manually edited out the caves from all of the previous replies, then just dropped in a relevant subject in the last of its replies.

So in your case, remove everything from its last reply and just put "What is it about video games that you enjoy?" and this will nudge it in the right direction. The AI seems to randomly draw from lore, its description, reminders, and recent QA without any logic to which is most important.

As an example, in a recent chat I accidentally ended a sentence with "/" instead of ".", two replies later AI ended its sentence with /.

It's just a thing. There's a few things you can do to help keep characters somewhat more intelligible. I don't know what you've done/tried yet, though.

Who downvoted me saying I loved the dev. That's not very nice.

Hmm, perhaps I spoke too soon. I put the custom code in the character's custom code section. I reloaded the chat tab. Then typed /print in the chat field. It gave me an "Executing custom code" status for a few seconds, but nothing happened. All I have on this browser is Ublock Origin, would that mess it up maybe?