Thread

1. heyjstn · 1790621368 · focus · HN ↗

   Have anyone tried a workflow that:

   - Fable 5.1 for planning/adversarial reviewer

   - Opus 5.5 for well-scoped tasks break down

   - Sonnet 5.5 for these well-scoped tasks implementation

   I think the blocker might be how efficient the context is compacted and sending around between these agents

   1. chrismustcode · 1790621483 · focus · HN ↗

      You might as well use Opus for everything there.

      Changing model would be cache busting spiking usage for no good reason when Opus can do it all.

      Haiku 5.5 might fit well though depending on pricing.

      1. SirMadam · 1790621882 · focus · HN ↗

         Do subagents share context? If Opus delegates to a different Sonnet window, I don't believe this busts cache?

         1. enraged_camel · 1790622458 · focus · HN ↗

            Subagents don't share context. But that's why delegating implementation to a subagent doesn't work well except for things that are truly mechanical in nature: the subagent needs to independently reason about the task it is given, and then the output will also be reasoned about by the main agent. So you end up wasting time and tokens.

            1. mnicky · 1790622731 · focus · HN ↗

               On the contrary, subagents save context overall, when the task is sufficiently large.

               Also, my experience is that Fable 5.1 is very good at prompting/orchestrating Opus/Sonnet subagents when working on a larger task (e.g. 1-2M context window use only for the orchestrator itself).

            2. esafak · 1790630701 · focus · HN ↗

               If you use subagents your main agent won't need to compact as often, with the loss of information that entails.

Unofficial Hacker News client; not affiliated with Y Combinator.