alt Hacker NewsThat should be covered by the harness rather than the LLM itself, no? Compaction and summarization should be able to allow the LLM to still run smoothly even on large contexts.
That should be covered by the harness rather than the LLM itself, no? Compaction and summarization should be able to allow the LLM to still run smoothly even on large contexts.
Sometimes it really needs a lot of data to work.