Writing, at its core, is a shared experience between the author and the reader—an exchange of thoughts, emotions, and ideas. This connection, built on trust and authenticity, is the bedrock of any meaningful relationship, even one as seemingly one-sided as the parasocial relationship between an author and their audience.

When AI is introduced into the realm of writing, it disrupts this delicate balance of trust. Readers inherently believe that they are engaging with the genuine thoughts and expressions of a fellow human being. However, the introduction of AI blurs this line, creating a scenario where the words on the page may not be the product of human experience or creativity.

Imagine delving into a piece of writing, believing you are connecting with the unique perspectives and emotions of another person, only to discover that those words were crafted by a machine. The sense of betrayal and disillusionment that may follow disrupts the very essence of the reader's trust in the author. It's akin to thinking you are having a heart-to-heart conversation with a friend, only to later realize it was an automated response.

This violation of trust erodes the foundation of the parasocial relationship, leaving readers questioning the authenticity of the connection. Human communication is a dance of shared experiences and emotions, and AI, no matter how advanced, lacks the depth of personal understanding that defines true human interaction.

In essence, while AI may expedite the writing process and provide creative insights, it does so at the cost of jeopardizing the sacred trust between the writer and the reader. As we navigate this digital era, let us not forget the importance of preserving the authenticity that underlies our human connections through the written word.

Generated by ChatGPT.

Hey, good people of Tildes!

I'm building a self-help web app, a small part of which I'd like to involve some pixel pets. I like pixel art and it'd be great if I could create some. Though, the truth is, I can't draw for shit, I have little to no imagination, and I'm afraid even if I put the time and effort into it, I still may not produce something I'd call good enough to put on the website. I also lack the motivation to spend a lot of time learning how to create good pixel art, as I only need it for this project.

I thought about paying some professional(s) to do it but that would probably break the bank for me, as I want to offer the users a lot of pixel pet options, which brings us to what I guess is the only remaining option.

I found some services that offer AI-generated pixel art. This one in particular looks like what I'm looking for and also offers animations. While watching a demo of it on YouTube, I noticed a few comments voicing concern about the ethics of selling art that's generated using models trained off of unpaid artists' work. While this is not a new topic, I admittedly hadn't given it much thought before, as I've never used, or planned to use AI-generated art in a meaningful capacity.

While I'm not sure whether it changes much, for what it's worth, I should note that my web app is going to be free, open-source, and ad-free forever.

What are your thoughts? Also, I'd love to know if there are options that I missed!

I have been having fun learning about generative AI. All in the cloud -- I got some models on hugging face to work, tried out Colab Pro, and found another cloud provider that runs SD models (dreamlook.ai if anyone is interested).

It's got me curious about trying to run something locally (mostly stable diffusion/dreambooth, possibly ollama).
I currently have a Thinkpad T490 with 16 gb ram and the base-level graphics card. I haven't actually tried to run anything locally, on the assumption that it would be extremely slow. I saw that you can get an external GPU, though I also saw some reports of headaches trying to get external GPUs up and running.

I am curious what a workstation might cost that could do a reasonable job running local models. I am not a huge gamer or have any other high performance needs that are not currently served by the Thinkpad; not sure I can justify a $3000 workstation just to make a few jpgs.

I would be happy to buy something secondhand, like if there was a good source of off-lease workstations.

Alternatively-- if you have a similar computer to the T490 and do run models locally, what sort of performance is reasonable to expect? Would it be enough to buy some more RAM for this laptop?

Thanks for any advice!

First, I headed to ChatGPT to pipe in my top 5 artists (as noted by Spotify). These may not really be my top 5, but I obviously listen to them a lot :).

Me: Spotify lists my top 5 most listened to artists as Greta Van Fleet, Mott The Hoople, Television, Steely Dan, and The Kinks. can you recommend 10 more artists you think I'll like?

ChatGPT: Based on your taste, you might enjoy Led Zeppelin, The Rolling Stones, Cream, The Who, Fleetwood Mac, Lynyrd Skynyrd, Eagles, Jethro Tull, The Doors, and Deep Purple. Give them a listen and see if they resonate with your musical preferences!

Me: Can you recommend some lessor known artists you think I'll enjoy?

ChatGPT: Certainly! Explore the source of The Black Angels, Rival Sons, Ty Segall, Temples, The Sheepdogs, King Gizzard & The Lizard Wizard, Khruangbin, Parquet Courts, Dr. Dog, and Allah-Las. These lesser-known gems might align well with your musical taste.

I've actually never heard or listened to any of these artists! Next, I listened to each artist's most popular songs. Here's my take:

The Black Angels: Listened to Young Men Dead and Black Grease. Both are really good songs. Definitely right up my alley. Added to my playlist.

Rival Sons: Listened to Do Your Worst and Open My Eyes. Really liking this artist and added to my playlist.

Ty Segall: Listened to My Lady's On Fire and My Room. On the fence, there's something here that I like. Continued to listen through to Every 1's a Winner, Feel, Girlfriend, Void, Eggman, and Tall Man Skinny Lady. I think Void and Eggman sealed the deal for me. This is definitely an artist I'll listen to. Really enjoyed some of the interesting, and unexpected, things that happened musically in these songs.

Temples: Listened to Shelter Song and Paraphaernalia. Not feeling it here.

The Sheepdogs: Listened to Feeling Good and I Don't Know - EP Version. On the fence, but it's not bad. Continued to listen to Please Don't Lead Me On and Nobody. Added to the playlist at this point. This artist has a Lynyrd Skynyrd vibe that I like.

King Gizzard & The Lizard Wizard: Listened to Gila Monster. Really enjoyed the musical composition, but the voices just aren't for me. I've never been a fan of this voice style and then the chanting of "Gila Gila" really isn't my thing. I decided to listen to more anyway and was suprised to hear vastly different styles with Work This Time, Sense, Slow Jam 1, and Theia. Still not going on my playlist, but some interesting tunes from this artist.

Khruangbin: Listened to Texas Sun, People Everywhere (Still Alive), Mariella, White Gloves, and B-Side. Love the mix of RnB and funk. Some really good grooves happening here. B-Side had me moving in my seat and this artist will definitely be on the playlist.

Parquet Courts: Listened to Tenderness, skipped Total Football due to the explicit tag and my preferences around that, and then continued listening to Outside, and Careers in Combat. I am a fan of this genre of music, but I am very particular in what I like and what I don't. I love The Dead Milkmen, Ramones, Television, and Dead Kennedys. This artist isn't giving me the feels.

Dr. Dog: Listened to Where'd All the Time Go, Nellie, Heart it Races - Cover Version, and The Breeze. During the first song, I knew this artist was going on the playlist. Got to Nellie and there was absolutely no doubt. Love the voices, the simple melodies, and the entire vibe.

Allah-Las: Listened to Houston, Caramaran, and Raspberry Jam. Really like the organ in this and it takes me back to The Doors, Steppenwolf, and The Animals. Both Houston and Raspberry Jam were instrumentals, and I wanted to hear more vocals, so I listened to Dust as well. This is some good music and is going on the playlist.

Overall, ChatGPT did a great job of recommending music that is now on my playlist. I'm desperately waiting for the day that I can have a conversation with my personal assistant, have it queue up music for me automatically, and then I give it feedback on what I heard. My personal assistant would then continue to shape my playlist based on my feedback. I know this day is coming soon, but it can't get here fast enough for me.

As a bonus, after I conducted this experiment Spotify immediately jumped into another artist I never heard of -- Drug Cabin. The first song played was Steely Dad and this is just a fantastic song.