Published:
The cost of overseeing many agents depends on how many breaks in continuity a human has to reconcile, not on how many agents run. Treat agents as procedures and tasks as objects: keep each task’s history in the repo, keep the human’s view to one screen, and let agents attach, act and exit.
Published:
Self-refine, self-play, self-evolve, RSI: in post-training one variable separates them, how much of the objective is handed to the agent. Order 0 is a plain code agent. Agents complete order 1 today; order 2 is done by pipelines humans design and agents execute; order 3 has never been done by a machine.
Published:
Self-refine, self-play, self-evolve, RSI: in post-training one variable separates them, how much of the objective is handed to the agent. Order 0 is a plain code agent. Agents complete order 1 today; order 2 is done by pipelines humans design and agents execute; order 3 has never been done by a machine.
Published:
The cost of overseeing many agents depends on how many breaks in continuity a human has to reconcile, not on how many agents run. Treat agents as procedures and tasks as objects: keep each task’s history in the repo, keep the human’s view to one screen, and let agents attach, act and exit.
Published:
The cost of overseeing many agents depends on how many breaks in continuity a human has to reconcile, not on how many agents run. Treat agents as procedures and tasks as objects: keep each task’s history in the repo, keep the human’s view to one screen, and let agents attach, act and exit.
Published:
Self-refine, self-play, self-evolve, RSI: in post-training one variable separates them, how much of the objective is handed to the agent. Order 0 is a plain code agent. Agents complete order 1 today; order 2 is done by pipelines humans design and agents execute; order 3 has never been done by a machine.