Re:GPT-4o's Memory Breakthrough (Needle in a Needlestack)
by sftombu on Tuesday May 14, 2024 @11:44PM
(#40362887)
The models benchmarked by RULER do worse in needle in a needlestack. It will be interested to see how 4o does with RULER.
[ Parent
| on HN ]
There are no comments on this comment yet.