← Back to context Comment by pelagicAustral 2 hours ago Is that right? Why the shit would that happen? 2 comments pelagicAustral Reply transdev12 2 hours ago Because they’ve essentially exhausted pre training scaling and are looking to post training to expand capabilities, which is really just optimization via reinforcement learning against specific tasks aka bench maxing. ctolsen 1 hour ago Their ambition isn't your work being amplified by their model, they want you running fifty autonomous long-running agents.
transdev12 2 hours ago Because they’ve essentially exhausted pre training scaling and are looking to post training to expand capabilities, which is really just optimization via reinforcement learning against specific tasks aka bench maxing.
ctolsen 1 hour ago Their ambition isn't your work being amplified by their model, they want you running fifty autonomous long-running agents.
Because they’ve essentially exhausted pre training scaling and are looking to post training to expand capabilities, which is really just optimization via reinforcement learning against specific tasks aka bench maxing.
Their ambition isn't your work being amplified by their model, they want you running fifty autonomous long-running agents.