I think it is meant to let them train one model that both can and can’t browse the web in different modes, and then let them hint the model’s current capabilities to it so it acts with the necessary self-awareness.
If they just wanted it to always say it can’t browse the web, they could train that in. I think instead they train it in conditioned on the flag in the prompt, so they can turn it off when they actually do provide browsing internally.
I think it is meant to let them train one model that both can and can’t browse the web in different modes, and then let them hint the model’s current capabilities to it so it acts with the necessary self-awareness.
If they just wanted it to always say it can’t browse the web, they could train that in. I think instead they train it in conditioned on the flag in the prompt, so they can turn it off when they actually do provide browsing internally.