If it turns out that capabilities and safety are not so dichotomous, and so robustness / interpretability / safe exploration / maybe even impact regularisation get solved by the capabilities lot.
If early success with a date-competitive performance-competitive safety programme (e.g. IDA) puts capabilities research onto a safe path.
Some more ways:
If it turns out that capabilities and safety are not so dichotomous, and so robustness / interpretability / safe exploration / maybe even impact regularisation get solved by the capabilities lot.
If early success with a date-competitive performance-competitive safety programme (e.g. IDA) puts capabilities research onto a safe path.