sisyphean

3.5 is also really good, but I've been using GPT-4 for almost everything since it became available. 3.5 hallucinates more often but I used it a lot before April, and I was really satisfied with it.

I implemented it. The feature will be available right from the start. The bot will reply this if the user has disabled it:

🔒 The author of this post or comment has the #nobot hashtag in their profile. Out of respect for their privacy settings, I am unable to summarize their posts or comments.

It will be me 😭

I limited it to 100 summaries per day, so it won’t cost more than about $20/month in the worst case.

I haven’t yet looked into it, but the screencast on its website looks really promising! I have a lot on my plate right now so I think I’ll release it first with the GPT-3.5 integration, but I’ll definitely try GPT4All later!

It can also summarize links, so it’s already useful even if there are few people posting walls of text

I have a question. If these were the final results (in descending order of votes):

• x~1~ votes for UBP icons for non-language-specific communities
• y~1~ votes for UBP everywhere
• y~2~ votes for colorful UBP everywhere
• x~2~ votes for colorful UBP icons for non-language-specific communities
• z votes for no UBP icons

Where y~1~ + y~2~ > x~1~ + x~2~, so more people wanted UBP everywhere but because of the two independent options (where to use them and what color), their votes got fragmented, what is the right course of action?

I think it would have been better to have two polls, one about the question of using visually consistent icons and another one about what they should look like.

This one:

https://github.com/SleeplessOne1917/lemmy-bot

If you want it to be really good, you can transcribe the audio even if the YouTube video already has a transcript. Whisper is much better than whatever YouTube uses for the subtitles. Of course it will be more expensive this way.

Oh, I’ve just realized that it’s also possible if the video doesn’t have a transcript. You can download the audio and feed it into OpenAI Whisper (which is currently the best available audio transcription model), and pass the transcript to the LLM. And Whisper isn’t even too expensive.

Not sure about the legality of it though.

Thank you:)

Unfortunately the locally hosted models I've seen so far are way behind GPT-3.5. I would love to use one (though the compute costs might get pretty expensive), but the only realistic way to implement it currently is via the OpenAI API.

EDIT: there is also a 100 summaries / day limit I built into it to prevent becoming homeless because of a bot

This is an excellent idea, and I'm not sure why people downvoted you. The bot library I used doesn't support requesting the user profile, but I'm sure it can be fetched directly from the API. I will look into implementing it!