‹ BackHN Continuity

Thread

Show HN: Lossless-memory – a personal AI memory that never summarizes

67 points · 34 comments · aru-labs

  1. theresLand · · focus · HN ↗
    Seems like this would break the cache often. That would increase billing rates with certain providers and, for local models, take a while to generate responses, especially with long-running agentic sessions. Interesting idea though.
    1. TimByte · · focus · HN ↗
      Placing LLL inside the user message right ahead of the new query keeps the common conversation prefix fully intact
Open on Hacker News to reply ↗

Unofficial Hacker News client; not affiliated with Y Combinator.