Re:Language Model Teams as Distrbuted Systems
by rando1234 on Monday March 16, 2026 @07:28PM
(#47406495)
Where we've had some success is with heterogeneous agents with some cheap quantised/local models performing certain tasks extremely cheaply that are then overseen or managed by a more expensive model.
[ Parent
| on HN ]
Re:Language Model Teams as Distrbuted Systems
by timcobb on Tuesday March 17, 2026 @01:22AM
(#47408962)
I've played with this type of thing and I couldn't justify it vs just using a premium model, which seems more direct and error proof. Cheap models in my experience could really consume tokens and generate cost