top | item 47209923

(no title)

nharada | 6 hours ago

Nice, I like the idea. It sounds like qualitatively you haven't had any performance regressions while doing this, but have you tested it at all on any sort of benchmark or similar eval? I'm curious how well the actual system performs with less context like this. I mean it's possible it actually improves...

discuss

order

No comments yet.