Re:Qwen3.6-Plus: Towards Real World Agents
by Someone1234 on Thursday April 02, 2026 @01:38PM
(#47617556)
It depends on the specific task.
For example: "Here our dataset that contains customer feedback comment fields; look through them, draw out themes, associations, and look for trends." Solving that with a deterministic program isn't a trivial problem, and it is likely cheaper solved via LLM.
Re:Qwen3.6-Plus: Towards Real World Agents
by cubefox on Friday April 03, 2026 @01:18AM
(#47623418)
It makes sense if the dataset is so large that LLM cost is a prohibitive factor. Otherwise a frontier LLM has the advantage of producing a better result.
For example: "Here our dataset that contains customer feedback comment fields; look through them, draw out themes, associations, and look for trends." Solving that with a deterministic program isn't a trivial problem, and it is likely cheaper solved via LLM.