what if I want to train a new model and run inference on it?
The API can also have built-in functions for training.
What if I want to experiment with a new scaffold?
Scaffolds can normally be built around APIs? I thought scaffolds was just all about what prompts you send to the model and what you do with the model outputs.
Scaffolds can normally be built around APIs? I thought scaffolds was just all about what prompts you send to the model and what you do with the model outputs.
Yeah I guess you could do filtering either at the API level or the scaffold level, so we may as well do it at the API level.
RE whether this is tractable, yeah I agree with the considerations in Buck’s post.
The API can also have built-in functions for training.
Scaffolds can normally be built around APIs? I thought scaffolds was just all about what prompts you send to the model and what you do with the model outputs.
I do agree that this might be rough for some types of research. I imagine the arguments are pretty similar here as the arguments about how much research can be done without access to dangerous model weights.
Yeah I guess you could do filtering either at the API level or the scaffold level, so we may as well do it at the API level.
RE whether this is tractable, yeah I agree with the considerations in Buck’s post.