-12
Honest breakdown of AI companion app memory systems after testing 40 platforms (thelemmy.club)
submitted 4 months ago by to c/fosai@lemmy.world
9 comments fedilink hide all child comments
 

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

all 9 comments

sorted by: hot top controversial new old
[–] 2 points 4 months ago (4 children)

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.

  • permalink
  • fedilink
  • source
  • hideshow 4 child comments
    •
  • [–] 1 point 4 months ago (2 children)

    its so weird that that is now mistrals "medium" size...

    weird to see em growing up like this...

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 2 child comments
    •
  • [–] [S] 1 point 4 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.

  • permalink
  • fedilink
  • source
  • parent
    • [–] 1 point 4 months ago (2 children)

    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.

  • permalink
  • fedilink
  • source
  • hideshow 2 child comments
    •
  • [–] [S] 1 point 4 months ago (1 child)

    No public analytics that I've seen platforms keep that close to the chest. From actually using these things though the ones that hold up seem to be doing selective memory extraction rather than dumping the full conversation history into every context window. Key facts, emotional markers, relationship milestones — that kind of thing. Which makes sense because a raw running log would be insane compute costs for a $15/month product. Still way more expensive than session-only chat which is probably why free tiers get quietly capped so fast.

  • permalink
  • fedilink
  • source
  • parent
  • hideshow 1 child comment
    •
  • [–] 1 point 4 months ago

    For sure. I can imagine these types of tools will keep getting bigger and leveraging massive amounts of data for a single user. There’s a future where the models are being tuned or even pre-trained (is that right?) on a regular basis. You’re in school. You get an AI assistant on your new laptop. It asks you some setup questions and tunes on the spot. After a month it pre-trains with your data and then continues to tune.

    I was thinking it must be unrealistic and kind of freaky as an AI companion to remember so many little things. As an assistant though, it’s great.

  • permalink
  • fedilink
  • source
  • parent
    • [–] 1 point 1 month ago

    The best memory system will be the one you can self host. Fuck all these companies

  • permalink
  • fedilink
  • source
    •