News for hackers. Stuff that matters.
Re:Rabbit R1, Designed by Teenage Engineering by vineyardmike on Tuesday January 09, 2024 @08:02PM (#38934763)
> As a bonus, those capabilities don't require uploading your data to the cloud or risking LLM hallucinations.

Ignoring that half those services are dependent on the cloud already, this is such a bold and hard problem. A solution would be magical but LLMs are our best chance.

Without clearly defined protocols (eg SMTP, CalDav) and a ton of boring to write and use case specific glue code, you’re really dependent on LLMs to make those M*N connections from one service/format to another. An LLM can turn any current or future input format into any current or future output format. That’s really powerful and basically unsolvable at scale with the tools we have now.

Re:Rabbit R1, Designed by Teenage Engineering by F7F7F7 on Wednesday January 10, 2024 @11:02PM (#38947407)
And what’s to be said about every large orgs or serious companies TOS against screen scraping data?
Re:Rabbit R1, Designed by Teenage Engineering by vineyardmike on Thursday January 11, 2024 @03:18AM (#38949280)
If they don't like screen scraping they probably also don't have an API and probably don't have 100 different ways to auto-export data.