News for hackers. Stuff that matters.

A comment on Show HN: Opper AI – Task-Completion API for LLMs.

Re:Show HN: Opper AI – Task-Completion API for LLMs by jlundberg on Tuesday July 15, 2025 @09:38AM (#44571052)
What are your thoughts on longetivity, i.e. depending on your service over time?

Do you have any public commitments in that regard?

Being able to run your application forever is one of the strong benefits I see with local models, besides being able to feed it with sensitive data.

[ Parent | on HN ]
Re:Show HN: Opper AI – Task-Completion API for LLMs by gsandahl on Tuesday July 15, 2025 @09:42AM (#44571091)
We have been thinking a bit about this, and one option would be to have some form of locally hosted runner. You can optimize the task in the cloud and deploy it locally. Something like that. It is possible to plug in custom models so technically feasible.
[ Parent | on HN ]