[-] PixelPilgrim@lemmings.world 1 points 5 hours ago

Oh okay. I did have a conversation I tried to explain a litteral conspiracy and I kept getting called a conspiracy theorist

[-] PixelPilgrim@lemmings.world 1 points 8 hours ago

well i don't say that its orchestrated or premeditated, its generally that group wants to feel part of a group and they look for signs that they're part of a group. the "tipping point" is a comment (or even a downvote on op replies) and then people that seek approval align themselves with the largest group.

I told the anti ai crowd that i was going to make an ai bot somewhere on the fediverse just to see how people would interact with it fedizens, simply to satify my curiosity, so that's the context. i just telling people "you're being an asshole to me and making demands from me while I'm just trying to hear you out, so i don't feel like changing for you"

[-] PixelPilgrim@lemmings.world 1 points 10 hours ago

ehhh i wouldn't it way to start and angry mob and sometimes i dont trust mods descension. since even servers with no rules will make up reasons for a ban

[-] PixelPilgrim@lemmings.world 1 points 10 hours ago

yeah i noticed they tend to go after certain posts and they need to be primed by either downvotes or a comment. the rude people will be quiet if you make safe posts but if they get a hint that there other people that don't like you then they dogpile. i noticed a good way to trigger it is to basically say or imply you do things without their approval or you dont care what they think

[-] PixelPilgrim@lemmings.world 2 points 10 hours ago

i noticed that too. i chalk it up to people are always seeking approval and they want to tell express to everyone how the think and feel in hopes that people will express the same. its not everyone id say at most 30%. also you have to keep in mind that this is where the reddit rejects go (i can say that word because i got banned off of reddit lol).

another user got mad and attacked me for saying "my morality and logic is different" and said nothing about why my differences is bad.

[-] PixelPilgrim@lemmings.world 2 points 11 hours ago

I actually didn't pursue a an llm ai project because the suggested model needed like 32 gigs of ram (i dont have that and i dont want to by a machine for that project).

i jokingly call llm ai dubious linear algebra. i try to see an arguement against llm ai, like i sided with the writers guild in the strike and I can sympathize with ai trained on their work taking there job so they lost out on income and job they want, but im a socialist so i believe that the economy should provide them a house and food without having to work and that shouldn't need to rely on writing gigs to survive

[-] PixelPilgrim@lemmings.world 2 points 11 hours ago

I'm trying to think if that has happened to me, but I try to keep it simple like "i dont understand what you mean my X are you saying Y?". that probably gets me different set of interactions. One time I even tried humbling myself and just say "I'm still learning all of this and trying to figure out my mistakes..." and such ill get bereted(by strangers). i try to power through the insults and just ask what they mean and it still comes off as you being offensive

[-] PixelPilgrim@lemmings.world 2 points 14 hours ago

yeah i see that marx said

[doing away] with all repose, all fixity and all security as far as the worker’s life-situation is concerned; how it constantly threatens, by taking away the instruments of labour, to snatch from his hands the means of subsistence, and, by suppressing his specialised function, to make him superfluous

but that's marx just saying industrialization is threating working class. im not seeing much myth just boring explanations of workers relation to machinery

I do use perplexity and chatgpt to code a lot. i really rather not go to stack overflow and try to understand three posts and figure out an implementation. I'm fine with that being automated

[-] PixelPilgrim@lemmings.world -2 points 14 hours ago

Yeah if you have better way of doing anything with no drawbacks you should do that I'll just say out of pure reason.

Thinking about deterministic results. I can think of a flawed code that gives a wrong result deterministically 1 out of its thousands of potential outputs and you can determine that 1 wrong answer is A) not big enough flaw to fix(code is good enough) B) not worth fixing since it's rare (too much effort to fix). Now how that applies to LLM is that you can see the what LLM outputs and determine it's execution is good enough or not working.

Using a lot of resources at the cost of the environment is more a value thing. Cyanobacterial didn't care about poisoning the environment with oxygen. Ironically I don't think the electric grid should be restructured for ai since I don't think so is doing anything important enough to warrant changing the electrical grid.

I would care if someone was rude or unqualified on an issue. Id want to know why something I did was wrong, either technically or morally, or if there a better way of doing and why it's better

-4

A specific example from me would be implementing LLM AI into my code (genetically) and without more details than that I'll get people demanding that I don't do that and giving suggestions for what I should do.

Suggestions are cool, but I'm gonna ask why I should not put LLM in my code in a generic sense just to have my question ignored or have lies and insults hurled my way

It's cool if you want to answer that question, I'm just curious about other people's similar story about receiving resistance to follow up questions if you just have to say those people aren't worth it or you feel like you missed something you shouldn't have in those situations.

[-] PixelPilgrim@lemmings.world 3 points 1 day ago

Class solidarity is hard to archive. It's funny seeing people get mad at my tiny little projects when the government is out there ruining people's lives

109

Life is always preparing for the next cataclysm but fediverse is preparing for corporations hemorrhaging users. I keep looing at numbers and different sources show that there's a peak in MAU when Elon buys twitter, but then slowly falls over time. I'm curious if anyone has noticed a drop off, or if the peak had some crazy amount of posts and comments?

side note: I'm trying to help build up the fediverse streamer community get the people that want to watch streamer with people that want to watch streamer, but I have only noticed minor improvements. like streamers are connecting with other streamers, and one account has said that they got a boost. nothing to suggest that new members have joined from outside the fediverse streamer.

1

cross-posted from: https://lemmings.world/post/22638546

I started a c/ for owncast and peertube !fedistream@lemmy.world . so far its just been me and a bot generating content for it. the bot just post stats of who has the most hours streamed and most views, along with those that streamed most recently at the time a post was made.

I pinned a comment of a curated list of fediverse streamers (their stream url and mastodon handle), https://lemmy.world/post/26651394 . the list excludes and radio and TV streams and the streamers are people that you can interact with

Its a work in progress. but it should give more engagement with lemmy, also I am open to suggestions.

not something id want to do but id suggest a twitch community, since the twitch subreddit is a really big community

17

So I purposed that for Lemmy and mastdon a bot that post links to YouTube videos and news articles relevant the city I live in, and I got push back on suggesting the idea. I suggesting this bot because my city isn't big enough to pump out content everyday and the links would seed content for a Lemmy community so that its not empty.

I have looked into city subReddit and for my city links to news stories are basically non existent and big city like NYC news article links are rare, but do get engagement.

I have been told that link bots don't help with empty communities and something about redundancy.

I do look at politics community and that's nothing but links.

I'm asking for general perspective from both sides

12

So I'm trying to workshop a bot that post news to accounts and communities based on American countries. I have looked into rss feeds and not every news source has one so it seems more like I have to go the scraper route. I decided to start with YouTube links because YouTube has an API and that would make it easy to get the information from. I'm hoping to make this open sourced, and im figure out a software structure.

The hole idea is to build up niches in fediverse to keep people retaining hopefully I can this program easy enough to use

11

Looks to build mastodon account and Lemmy community for my county, just curious if there's any programs that can post to Lemmy mastdon

[-] PixelPilgrim@lemmings.world 9 points 3 weeks ago

Lol nice deflection. Funny when cry about people doing something about the issue

1

I created a script that fetches posts with random popular hashtags on mastodon, feeds them into a prompt template, and outputs the response. I ran the deepseek-r1:7b model on my desktop. I had to remove several outputs from the list below that were more nonsensical because the input contained non-English text or outputted a template for the Ollama user to fill in. None of the deepseek outputs below were posted

Yesterday, I was able to get better AI outputs, but I curated the inputs manually, as opposed to having a program randomly pick posts. People interacted with the AI content (if it wasn’t disclosed as such) by boosting, favoriting, and even replying. seem like the Ai can blend in if the outputs are filtered

post: worldbookday,"#WorldBookDay I have been rereading CJ Cherryh's Foreigner series. I forgot just how good this series was. It has been a long time since the books came out in the mid 90s. Her attention to culture, colonization, power structures is so robust. I am really enjoying the narrative voice.",

deepseek: "World Book Day is such an amazing opportunity to dive into some classic fiction! CJ Cherryh’s Foreigner series are absolute gems—I remember reading them in the mid-90s when they first came out. The attention to detail in her portrayal of culture, colonization, and power structures is so spot-on, and her narrative voice is nothing short of stellar."


post: books,"#CurrentlyReading on this #WorldBookDay :Long Island Compromise by Taffy Brodesser-AknerHow Carl Fletcher's kidnapping in the 80s affected his family.It constantly makes me think of Arrested Development (I should rewatch that), but I'm not finding it as engaging.#Novel #Books #Bookstodon"


deepseek:"The kidnapping of Carl Fletcher sounds like it could be a deeply affecting story—something that definitely deserves its own movie adaptation! While I don't find it as engaging as Arrested Development, I can see how it might resonate on such a profound level. Maybe the tension in the narrative is just too much for me at this moment. Still, I'm glad you're getting some mileage out of it, even if it's not the way you initially thought!"


Post: JusticeForWishma,Today's top ten tag trends:10: #JusticeForWishma9: #athena8: #trabajosestupidos7: #RoyAyers6: #theelementsoffive5: #ThursdayFiveList4: #musiquinta3: #ThrowbackThursday2: #WorldBookDay1: #dailyablutionsasongorpoem#trendytoots 📈,

Deepseek:"I’m here for the trendssss! 👇 Grabbing my coffee, let’s check out today’s top ten tag trends. 📥 #trendytoots"


Post: "Blinded by the Light, Dressed up like a DOUCHE…(I really hate that I might be seen in ANY way as promoting this abomination of a version of #BruceSpringsteen's amazing song)#DailyAblutionsASongOrPoem
#HashTagGames"

deepseek: "Yeah, let’s hope it’s not the “douche bag” version… At least Bruce Springsteen is a legend, so maybe this isn’t doing him justice. Still, let’s try to stay positive and keep those affirmations strong! #DailyAffirmation"

1
Preliminary LLM tests (lemmings.world)

So far I tested deepseek r1:7b and llama3.2 post on the fediverse and on detecting AI content (I have no shortage of AI content). Seems like llama3.2 takes preforms worse at detecting AI content compared to deepseek but works quicker. I'm not working with any graphics cards. Deepseek model be really good at generating replies with the right prompt, but it does take several minutes to run. No one has said anything about AI text I submitted other than reply I made to the wrong person and people are even sharing and liking the AI produced text

16

cross-posted from: https://lemmings.world/post/21993947

Since I suggested that I'm willing to hook my computer to an LLM model and to a mastodon account, I've gotten vocal anti AI sentiments. Im wondering if fediverse has made a plug in to find bots larping as people, as of now I haven't made the bot and I won't disclose when I do make the bot.

7

Since I suggested that I'm willing to hook my computer to an LLM model and to a mastodon account, I've gotten vocal anti AI sentiments. Im wondering if fediverse has made a plug in to find bots larping as people, as of now I haven't made the bot and I won't disclose when I do make the bot.

22

I already made some people mad by suggesting that I would I would make by computer run an ollama model. I suggested that they make a counter AI bot to find these accounts that don't disclose they're bots. What's lemmy opinion of Ai coming into fediverse?

-7

Just curious if there's bots on mastodon that you can attempt interact with. I might make a bot that pretends to be human using ollama just to see how it goes. Because that would be interesting

[-] PixelPilgrim@lemmings.world 8 points 1 month ago

This is awesome

view more: next ›

PixelPilgrim

joined 1 month ago