Absolutely. I will go with a counterfactual and assume we don’t mean literally 3.5 but a model using the same architecture, level of compute, and scale but has been cleaned up and fine tuned for productive tasks.
Current theme: default
Less Wrong (text)
Less Wrong (link)
Absolutely. I will go with a counterfactual and assume we don’t mean literally 3.5 but a model using the same architecture, level of compute, and scale but has been cleaned up and fine tuned for productive tasks.