Ask HN: Do subagents stop making sense at some point?

1 points by nemath ↗ HN
If we have really powerful models (AGI) - would it still make sense to have subagents that have access to specific tools and has specific context?

Wouldn't the overlord model just do everything?

3 comments

[ 3.0 ms ] story [ 30.2 ms ] thread
The overlord model might be expensive to run, take a long time, etc.
So even if things become cheaper to run and faster to run there will always be a use case for a submodel?
Do you have GI? Does it makes sense for you to use a subagent?

Anyhow, a solar-powered calculator (cost: approximately $0) gives a more reliable and more efficient answer than $100 billion and 100GW of AI.