sisyphean

joined 1 year ago
MODERATOR OF
[–] sisyphean 8 points 1 year ago

Finally I could get into the beta and all I can say is wow, I’m in love with this app 🤩

Keep up the good work!

[–] sisyphean 2 points 1 year ago

Quality shitpost

[–] sisyphean 2 points 1 year ago

Yes, there are so many possibilities for GPT-powered bots. I want to implement a couple more.

[–] sisyphean 3 points 1 year ago

It’s a Node.js app because the Lemmy-bot library is for Node.

I will definitely open source it, but the code is currently in a disgusting state, so I need to clean it up first.

[–] sisyphean 2 points 1 year ago

It’s still in preview, I can’t access it either, only a select few on Twitter who post about it all the time and make me jealous:)

[–] sisyphean 2 points 1 year ago (1 children)

Yes, OpenAI and out of pocket. Unfortunately cheaper or self-hosted models are much worse.

[–] sisyphean 1 points 1 year ago

It has also been very useful to me. I use it for learning, programming and organizing my thoughts and to-dos. I also ask it for advice if I’m stuck and I have no motivation for something.

And I can definitely relate to falling down the rabbit hole… I even started a Lemmy community about AI…

[–] sisyphean 3 points 1 year ago

Thank you, that’s a reasonable suggestion, I added it to the comment template:

TL;DR: (AI-generated 🤖)

[–] sisyphean 1 points 1 year ago

Yes, I also realized Whisper could be used for this (see sibling comments, I guess they didn’t show up in your inbox).

[–] sisyphean 1 points 1 year ago

Yes, they have promised explicitly not to use API data for training.

Thank you, I’ll take a look at these models, I hope I can find something a bit cheaper but still high-quality.

[–] sisyphean 2 points 1 year ago

Unfortunately I don’t yet have access to it so I can’t check if the description always comes first. But your theory sounds interesting, I hope we’ll be able to find out more soon.

 
 
44
Ho to make sushi (programming.dev)
 
53
Ho to make sushi (programming.dev)
 
 
 
 
20
submitted 1 year ago by sisyphean to c/auai
 

Trick the LLM into revealing a secret password through increasingly difficult levels.

 

OP actually went to the café as a joke but GPT-4 didn’t show up.

4
submitted 1 year ago* (last edited 1 year ago) by sisyphean to c/auai
 

Using AI to get constructive criticism and avoid cognitive biases.

 

There’s a lot of AI/crypto bro type sigma grindset blogspam on the internet about artificial intelligence. It’s really hard to separate the wheat from the chaff and find actually useful or interesting content.

Join us if you want to learn more about AI or share what you learned in a friendly and constructive community.

Links

view more: ‹ prev next ›