Comment by nearbuy
4 hours ago
Given that they're just using it to avoid the googling for bash command syntax, I'm not sure they'll save in the end against the 140k training examples they generated.
4 hours ago
Given that they're just using it to avoid the googling for bash command syntax, I'm not sure they'll save in the end against the 140k training examples they generated.
Good observation! It would have to be offset with O(140k) queries to the model, which is, well, unlikely.
Just like with OSS in general, being able to distribute it is what makes the effort worthwhile.
This particular example is maybe a niche, but 1400 people can use a few hundred queries in a reasonable amount of time.
If it's about the latency / flow disruption, spending a few hours once could easily be worth it if the result is actually good enough to skip googling/retries.
you can probably generate quite a few example pairs in a single shot, you also likely don't need the best models for this either