Hacker News Reader

We have to add LLMs and MMMs (multi modal models) into all standard Linux distributions. A service will index all local files creating embedding connectors, this will be used to augment user prompts, and voila we can search for anything with natural language.

View on HN

Once models / inference engines are performant enough to run on consumer hardware without hogging all the resources of a machine -- sure! Embedding this into the core of a linux system sounds very interesting. A shell interaction could be had in nerd gobbledygook or plain human language.

> We have to add LLMs and MMMs (multi modal models) into all standard Linux distributions.

Why? This seems like a quick road to remote-execution-vuln-as-system-service.

> and voila we can search for anything with natural language.

What if your model keeps misunderstanding you?

Reply on news.ycombinator.com