Hacker News new | ask | show | jobs
by TheGeminon 861 days ago
Outperform is dependent on the RAG approach (and this would be a RAG approach anyways, you can already do this with smaller context sizes). A simplistic one, probably, but dumping in data that you don't need dilutes the useful information, so I would imagine there would be at least _some_ degradation.

But there is also the downside of "tuning" the RAG to return less tokens you will miss extra context that could be useful to the model.

1 comments

Doesn't their needle/haystack benchmark seem to suggest there is almost no dilution? They pushed that demo out to 10M tokens.