Yash Patil
@ypatil125
Most companies aren't leveraging their most valuable asset - their traces.
There’s a ton of software value to build around raw inference and models like Jev open up a whole new set of possibilities because of their architecture and how cheap they are to run.
When you’re
There’s a ton of software value to build around raw inference and models like Jev open up a whole new set of possibilities because of their architecture and how cheap they are to run.
When you’re
Bryan Lee@_brylee10 · Sep 23I implemented a system in @appliedcompute’s platform for automated failure mode clustering with Jev to surface errors at an even larger scale than before.
RL training produces billions of tokens in traces. I always manually read many traces to understand model behavior, but
RL training produces billions of tokens in traces. I always manually read many traces to understand model behavior, but
0:16 · Edited
19 156