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

  • tal@lemmy.todayEnglish
    1·
    2 months 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.

      • Companaya@lemmy.worldOPEnglish
        1·
        2 months ago

        Right? A year ago 70B felt massive and now it’s basically mid-tier. The pace of this is genuinely hard to keep up with even when you’re paying close attention to it.

    • Companaya@lemmy.worldOPEnglish
      1·
      2 months ago

      Fair point and you’re right I should have said largest commonly deployed in consumer companion apps rather than largest period. Behemoth at 123B exists but none of the platforms I tested are actually running that in production. Sloppy phrasing on my part, appreciate the correction.