← Back to context

Comment by theplumber

4 days ago

Why do I find it dummer/even more superficial than opus 4.8? It just continued a session and I had to stop it because it become obviously “lost”

Massive performance degradation is expected when continuing a session with a different model

  • Is it? Is there a paper that covers this?

    I would've thought it should be mostly seamless, since it's being fed the entire conversation all along anyway.