Firehose

Filtered to Papers, tagged “hybrid models” · clear filters

All PeopleCompaniesPapersPodcastsHacker News

Browse by tag

14 SEP 2026 · Paper

This paper investigates the losslessness of a new language model architecture called Orthrus, which claims to achieve exact output sequences through a speculative decoding mechanism. The study finds that the architecture's performance depends on the numerical precision used, and that downstream task performance is not necessarily affected by the losslessness of the speculative decoding.