hperrin

A fully automated, on demand, personalized con man, ready to lie to you about any topic you want doesn’t really seem like an ideal product. I don’t think that’s what the developers of these LLMs set out to make when they created them either. However, I’ve seen this behavior to a certain extent in every LLM I’ve interacted with. One of my favorite examples was a particularly small-parameter version of Llama (I believe it was Llama-3.1-8B) confidently insisting to me that Walt Disney invented the Matterhorn (like, the actual mountain) for Disneyland. Now, this is something along the lines of what people have been calling “hallucinations” in LLMs, but the fact that it would not admit that it was wrong when confronted and used confident language to try to convince me that it was right, is what pushes that particular case across the boundary to what I would call “con-behavior”. Assertiveness is not always a property of this behavior, though. Lately, OpenAI (and I’m sure other developers) have been training their LLMs to be more “agreeable” and to acquiesce to the user more often. This doesn’t eliminate this con-behavior, though. I’d like to show you another example of this con-behavior that is much more problematic.

A fully automated, on demand, personalized con man, ready to lie to you about any topic you want doesn’t really seem like an ideal product. I don’t think that’s what the developers of these LLMs set out to make when they created them either. However, I’ve seen this behavior to a certain extent in every LLM I’ve interacted with. One of my favorite examples was a particularly small-parameter version of Llama (I believe it was Llama-3.1-8B) confidently insisting to me that Walt Disney invented the Matterhorn (like, the actual mountain) for Disneyland. Now, this is something along the lines of what people have been calling “hallucinations” in LLMs, but the fact that it would not admit that it was wrong when confronted and used confident language to try to convince me that it was right, is what pushes that particular case across the boundary to what I would call “con-behavior”. Assertiveness is not always a property of this behavior, though. Lately, OpenAI (and I’m sure other developers) have been training their LLMs to be more “agreeable” and to acquiesce to the user more often. This doesn’t eliminate this con-behavior, though. I’d like to show you another example of this con-behavior that is much more problematic.

cross-posted from: https://lemmy.ca/post/43297441

I just started working on a self hosted Android & iOS ereader app. I’d like to know what features you would like to see if you use this kind of app.

Current Planned Features

• Support for EPUB, TXT, and HTML ebooks.
• Syncing over WebDAV. (Bring your own server. I’m not hosting people’s pirated libraries.)
• Multiple libraries (a WebDAV server is a library), and multiple users per library.
• Current progress from offline reading will get synced when back online.
• Dark mode.
• Custom fonts and themes.
• Text to speech.
• Keep awake.
• Orientation lock.
• Open source. (GPL license)
• Native apps using React Native.
• Animations can be turned completely off.
• Really good e-ink screen support.
• Tablet and phone sized device support.

Background

I use a Boox Palma, but sometimes I don’t have it with me, and I’d like to read on my iPhone.

With the current ereaders I know of, there’s always some downside. Syncing costs money, rendering is janky, page turn animations can’t be disabled, themes cost money (really???), no cross platform support, etc.

I want to learn how to build native apps with React Native, so I’m using this as a learning project. I’m not trying to make money on it, so it’ll be open source, and you have to have your own WebDAV server with all your ebooks on it to sync.

Non-Planned Features

Some things I just can’t do or won’t help me learn, so I’m not going to do them.

• PDF support. (Maybe in the future, but not the initial version.)
• Web app. (I don’t want to host it.)
• Kindle app. (React Native doesn’t support them.)
• Syncing over anything but WebDAV. (I’ll be using WebDAV properties, and I’m not interested in doing any other providers.)

So I’d like to know, what are some features you would like to see, and what are the pain points you’ve experienced with your current ereader apps?

cross-posted from: https://lemmy.ca/post/43297441

I just started working on a self hosted Android & iOS ereader app. I’d like to know what features you would like to see if you use this kind of app.

Current Planned Features

• Support for EPUB, TXT, and HTML ebooks.
• Syncing over WebDAV. (Bring your own server. I’m not hosting people’s pirated libraries.)
• Multiple libraries (a WebDAV server is a library), and multiple users per library.
• Current progress from offline reading will get synced when back online.
• Dark mode.
• Custom fonts and themes.
• Text to speech.
• Keep awake.
• Orientation lock.
• Open source. (GPL license)
• Native apps using React Native.
• Animations can be turned completely off.
• Really good e-ink screen support.
• Tablet and phone sized device support.

Background

I use a Boox Palma, but sometimes I don’t have it with me, and I’d like to read on my iPhone.

With the current ereaders I know of, there’s always some downside. Syncing costs money, rendering is janky, page turn animations can’t be disabled, themes cost money (really???), no cross platform support, etc.

I want to learn how to build native apps with React Native, so I’m using this as a learning project. I’m not trying to make money on it, so it’ll be open source, and you have to have your own WebDAV server with all your ebooks on it to sync.

Non-Planned Features

Some things I just can’t do or won’t help me learn, so I’m not going to do them.

• PDF support. (Maybe in the future, but not the initial version.)
• Web app. (I don’t want to host it.)
• Kindle app. (React Native doesn’t support them.)
• Syncing over anything but WebDAV. (I’ll be using WebDAV properties, and I’m not interested in doing any other providers.)

So I’d like to know, what are some features you would like to see, and what are the pain points you’ve experienced with your current ereader apps?