Hacker News Reader

LLMs are stateless. But given an actual database of task-shaped items and some work, I could see the potential.

With a canonical source of truth, and set input/output expectations, the potential blast radius is quite small.

And the end results is.....? What? A todo app that takes 16GB of RAM?

Nothing that Mac and Windows users aren't already used to.

It’s tempting to be flippant about MacOS/windows but in all seriousness, the resources required for an LLM to do the job of a typical lighter weight app/software is a serious consideration. No amount of bloat matches what an LLM needs.

> No amount of bloat matches what an LLM needs.

I don't think that's necessarily true. For instance, LinkedIn uses more memory than Gemma E2B inference does.

LinkedIn is an entirely different category and an extreme case at that. We’re not talking about LLM’s replacing LinkedIn either. It’s an entirely different comparison/discussion.

Finally, we've fully documented the Singularity-is-actually-just-bloated software.

Reply on news.ycombinator.com