On top of this, I’d add that labs experimenting heavily with multi-agent workflows don’t exactly have token limits to worry about :)
It would be great to have Fable or Astra launch their own subagents, and then ask Fable and Astra to cross-check each other’s work. But at today’s prices, that would cost a fortune.
Yes! In my company we are usually working with claude code to ship features, and have codex hooked up to github to review every opened pr before the teviewer even see it.
But that is pricey, especially if you will count 150+ software engineers working all the time.
On top of this, I’d add that labs experimenting heavily with multi-agent workflows don’t exactly have token limits to worry about :)
It would be great to have Fable or Astra launch their own subagents, and then ask Fable and Astra to cross-check each other’s work. But at today’s prices, that would cost a fortune.
Yes! In my company we are usually working with claude code to ship features, and have codex hooked up to github to review every opened pr before the teviewer even see it.
But that is pricey, especially if you will count 150+ software engineers working all the time.
I can't even grasp the cost.