Live data from Hacker News

Local AI needs to be the norm

unix.foo

801–804 of 804 posts

Re: Local AI needs to be the norm

#802

Earlier quoted context omitted.

There is some recent work on modularizing knowledge in LLMs. https://arxiv.org/html/2605.06663v1 It might be possible to train a big generalist that is a composition of modules, some of which can be dropped dynamically at inference time, depending on the prompt.

Cool. Thanks for sharing. I am thinking about creating a series of smaller models for specific purposes and then orchestrating them so they mirror the human brain which is a bunch of subsystems that give multiple opinions about the same stimulus

Interesting direction. I’ve also been thinking about modular / subsystem-based approaches for specialized tasks in small AI systems.

Re: Local AI needs to be the norm

#803
post #542
post #532

Earlier quoted context omitted.

Do we even have decent OCR nowadays? Any free solutions?

The qwen models not only have good OCR, they will describe pictures to you.

They not not only describe pictures. They can analyze pictures. Detect anomalies. Create 3d models out of it.

Re: Local AI needs to be the norm

#804

For the mainstream audience, the sentiment around local ai today is the same that they had around open source a few decades ago. For a few products, some paid solutions were so much more advanced that open source were very often completely overlooked. Why bother ? And the like. Then we had captive SaaS and other plateforms and now it's obviously wrong for most of us. The dependency we have with anthropic and openai f…

I’m just waiting for the US Government to implement their own local AI. Which will eventually lead to them open sourcing it because it’s tax payer funded and being that the NSA has decades worth of internet data they can train on; open weights would be just as good as any companies…

How does it help?
Post reply on HN