Memory is the most marketed and least delivered feature in the AI companion space. Most platforms claim to remember you but either reset between sessions or just pull from a profile you filled in manually. After two years of testing the ones that actually carry real conversational context across weeks are rare. Just published a full breakdown of which platforms actually deliver on this versus which ones are just marketing: medium.com/@companaya/nomi-ai-review-2026-is-it-worth-it-tested-c91811dcb24a

  • venusaur@lemmy.worldEnglish
    1·
    15 hours ago

    Any analytics on token usage?

    Cool, but I can’t imagine how compute heavy it is to keep a running log of interactions and constantly include it in the context window and/or RAG. Week to week, sure, but over months to a year is wild, especially if you’re talking to it all day every day.

  • tal@lemmy.todayEnglish
    1·
    16 hours ago

    Soulkyn AI runs a 70B parameter model, the largest underlying language model available in any AI companion platform in 2026.

    Llama 3-based stuff is 70B, but it’s not the largest out there. Not even the largest open-weight model. Off the cuff, Behemoth is based on Mistral Large, at 123B.