To me the clear limiting factor to RSI right now is the lack of real continual learning. Current models forget too quickly and struggle to maintain attention on larger context windows to make huge progress within runs. But they can make more than zero self-improvement, which is enough to be dangerous.
To me the clear limiting factor to RSI right now is the lack of real continual learning. Current models forget too quickly and struggle to maintain attention on larger context windows to make huge progress within runs. But they can make more than zero self-improvement, which is enough to be dangerous.