Jordan Hochenbaum

@jnatanh

ML | Data | Engineering | Music. Currently VP, AI @BetterUp. Prev. Co-founder @KadenzeOfficial, CTO Nirveda Cognition (Aq'd), @Twitter, Prof. @CalArts.

following
followers

Jev sub-calls reportedly cost half as much and run 6× faster than Haiku 5.5 on OOLONG at 1M tokens

A user says they swapped Jev into recursive language models' sub-calls and examined abstention and routing to bigger models.

2 Sources, 20d ago, first seen 20d ago

Featured in

Jev sub-calls reportedly cost half as much and run 6× faster than Haiku 5.5 on OOLONG at 1M tokens

Featured in

Jev sub-calls reportedly cost half as much and run 6× faster than Haiku 5.5 on OOLONG at 1M tokens