Birbla

Join the discussion

Write your take first — we'll ask for email only when you're ready to publish.

Sign in
  • Hacker News
  • How is this different than https://github.com/obra/episodic-memory?
    by schainks
  • I have two questions: how a user can inspect the original source when the AI’s derived memory changes? Is chronology/versioning becoming more important than semantic summaries?
    by syndiary
  • Have you thought about using llm-wiki? It's pretty powerful and works well.
    by rbansal2
  • 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.
    by theresLand
  • As long as the relative time parser is hardcoded for japanese, english sessions are stuck with manual ISO dates. Wiring up dateparser or duckling would take an evening , so leaving that on the roadmap is an odd choice
    by TimByte
  • It may seem useful at first, but eventually you'll hit a wall where this doesn't work, and you have to add another memory technique. Eventually you end up with a complex multi-layered system, because what people want by "memory" is actually 10 different things which all need their own solution.
    by 0xbadcafebee
  • Is the date really useful? Usually I want the AI to remember rules, like "always do X before committing Y" and a timestamp doesn't change anything there.
    by StilesCrisis
  • Thank you for your questions. I have posted all the answers in the GitHub FAQ. Please take a look. Best regards. https://github.com/aru-labs/lossless-memory/blob/main/docs/f...
    by aru-labs

Explore Birbla archives