Remix.run Logo
Remix clone Hacker News
new | show | ask | jobsGithub
▲ kubb a day ago

Good observation! It would have to be offset with O(140k) queries to the model, which is, well, unlikely.

▲Lalabadie a day ago | parent | next [-]

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.

▲8n4vidtmkvmk a day ago | parent [-]

This example is not that niche. Lots of people use human to bash. I'd probably use a small pre trained model if it was easy to use. I use a little script right now that calls a cheap model. Actually.. $5 would probably will last me over a year so the only real benefit would be if I didn't have an internet connection.

▲computably a day ago | parent | prev [-]

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.