home.social

#byota — Public Fediverse posts

Live and recent posts from across the Fediverse tagged #byota, aggregated by home.social.

  1. 3/X “But there are algorithmic feeds for Mastodon?” — Yes, great tools exist, for example:

    ➡️ #BYOTA by @mala
    ➡️ #FediView by @adamghill
    ➡️ #Fedialgo by @pkreissel

    .. but most are client-side. They can rerank your existing timeline, but can't make #recommendations from outside your follower bubble.

  2. 3/X “But there are algorithmic feeds for Mastodon?” — Yes, great tools exist, for example:

    ➡️ #BYOTA by @mala
    ➡️ #FediView by @adamghill
    ➡️ #Fedialgo by @pkreissel

    .. but most are client-side. They can rerank your existing timeline, but can't make #recommendations from outside your follower bubble.

  3. CW: AI, LLMs

    blog.mozilla.ai/llamafile-retu

    has been instrumental in my first projects relying on language models (I purposely left “large” aside, as the one I used for is tiny).

    While looking for support for more recent models I tried other applications, but I never felt “at home” with them as I did with llamafile. This is why I am so happy of this move: breathing new life into it is, for me, giving ppl a new chance to better understand (what ppl now call) “#AI” while tinkering with it.

  4. Uuuh the video of the #BYOTA speed demo at #fediforum2025 is online! :partyparrot:

    spectra.video/w/xtZeTuwpYAqPsz

    If you missed the event, check this page out for videos of keynotes and demos and session notes: fediforum.org/2025-06/ 🔥

  5. Uuuh the video of the speed demo at is online! :partyparrot:

    spectra.video/w/xtZeTuwpYAqPsz

    If you missed the event, check this page out for videos of keynotes and demos and session notes: fediforum.org/2025-06/ 🔥

  6. Uuuh the video of the #BYOTA speed demo at #fediforum2025 is online! :partyparrot:

    spectra.video/w/xtZeTuwpYAqPsz

    If you missed the event, check this page out for videos of keynotes and demos and session notes: fediforum.org/2025-06/ 🔥

  7. Uuuh the video of the #BYOTA speed demo at #fediforum2025 is online! :partyparrot:

    spectra.video/w/xtZeTuwpYAqPsz

    If you missed the event, check this page out for videos of keynotes and demos and session notes: fediforum.org/2025-06/ 🔥

  8. In , we use to calculate *sentence embeddings*.
    If you don’t know what embeddings are, just think about them as numerical descriptors of your Mastodon statuses, which are closer (as in two cities’ coordinates being close on a map) the more semantically similar their respective statuses are. We’ll get back later to this with a more visual description. If you are interested in embeddings and wanna delve deeper, see vickiboykis.com/what_are_embed by @vicki.

  9. In #BYOTA, we use #llamafile to calculate *sentence embeddings*.
    If you don’t know what embeddings are, just think about them as numerical descriptors of your Mastodon statuses, which are closer (as in two cities’ coordinates being close on a map) the more semantically similar their respective statuses are. We’ll get back later to this with a more visual description. If you are interested in embeddings and wanna delve deeper, see vickiboykis.com/what_are_embed by @vicki.