Join the discussion

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

  • Hacker News
  • Rather than handcrafting solutions like it’s 1993, why not make robustness against forgetting part of the training objective?

    Let the search algorithm figure it out.

  • I appreciate that people are going beyond RAG and few shot prompting.
  • Great writeup. Are there any libraries that implement some of the methods described?

Explore Birbla archives

The Continual Learning Problem · Birbla