A Better Mastodon Client

Re:A Better Mastodon Client by sigmar on Thursday December 21, 2023 @09:54AM (#38721158)

I like the concept of "social media delivers a dumb feed, then my device groups and organizes them." In line with what is written in the conclusion, I would love to use a client like this that also does curation (by floating topics to the top once it starts seeing which topics you click on most) and then allowing interrogation/tuning of these recommendations. Why use openai instead of a local model though? (I'd imagine mistral-8x7-instruct would do well with the summarization task)

[ Parent | on HN ]

Re:A Better Mastodon Client by ekianjo on Thursday December 21, 2023 @10:49AM (#38721974)

mistal 7b base model is good enough for summarization. No need to go to the 8x7 one.

[ Parent | on HN ]

Re:A Better Mastodon Client by tkellogg on Thursday December 21, 2023 @01:17PM (#38724329)

OP here. Yeah, it’s also extremely low-risk. The sensitive part of the algorithm is the embeddings. This part is just making the group human readable.

The reason I didn’t do mistral the first time is because I’m lazy. I gave myself 3-4 hours to get a first pass done, and getting a local model running seemed unnecessarily difficult. It would be a great addition though.

[ Parent | on HN ]

Re:A Better Mastodon Client by charcircuit on Thursday December 21, 2023 @11:45AM (#38722867)

Each device being sent the firehose does not scale. You need another service to at least do the candidate generation from the firehose to get a reasonable rate for your device to handle.

[ Parent | on HN ]

Re:A Better Mastodon Client by PaulHoule on Thursday December 21, 2023 @12:04PM (#38723150)

I have a system that filters RSS feeds like this, out of 7000 articles it might pick 300 to show me, it takes just a few minutes to build and validate a model on a rather powerful PC so so far performance is not a problem.

If I were wanting to offer this kind of service to other people I know I could get an economy of scale just ingesting RSS feeds once, I think a lot of users might be happier sampling items from the firehose instead of curating a feed list, and I'd probably give up on the pure content-based filtering and include some collaborative filtering because people would perceive that it learns faster.

[ Parent | on HN ]

Re:A Better Mastodon Client by greggyb on Thursday December 21, 2023 @01:09PM (#38724185)

That is exactly what is happening here. The Mastodon server is handling the firehose, and creating sub-streams for each user based on followed accounts and tags.

[ Parent | on HN ]

Re:A Better Mastodon Client by ganzuul on Thursday December 21, 2023 @05:10PM (#38727763)

Video streaming seems like a firehose.

Do you mean the battery could not handle the LLM?

[ Parent | on HN ]

Re:A Better Mastodon Client by NewsyHacker on Thursday December 21, 2023 @01:54PM (#38725012)

Is unlimited user-end filtration and sorting seen as compatible with the spirit of Mastodon? Members of the Mastodon founding generation have sometimes expressed a wish for that founding generation to always remain visible and prominent, even as the user base expands. Part of it is that the founding generation is heavily trans, and they don’t want their identities and voices to be drowned out by wider cis society.

[ Parent | on HN ]

Re:A Better Mastodon Client by mcv on Friday December 22, 2023 @01:59AM (#38731684)

Is the spirit of Mastodon that the site, rather than the user, decides what the user sees? That wouldn't make them much better than the commercial platforms. I absolutely want users to be in control of their feed, so I welcome projects like these.

(I'm not actually on Mastodon but on Friendica, but I follow a lot of people on Mastodon.)

[ Parent | on HN ]