[becomevocal]

First thought was "only 30 tasks" however the findings map to what I've seen personally: code review consumes majority of tokens

[zozbot234]

Code review could also be run as an unattended/batched task though, possibly with at least some use of on-prem inference (which excels at this). That would be a major saving compared to the usual cloud inference scenario.

[jwnin]

with which models, though?

[becomevocal]

Yeah wasn’t there a report recently on how local models after energy costs didn’t weren’t actually more efficient to complete the same task?